Publications

B-cos Networks have been shown to be effective for obtaining highly human
interpretable explanations of model decisions by architecturally enforcing
stronger alignment between inputs and weight. B-cos variants of convolutional
networks (CNNs) and vision transformers (ViTs), which primarily replace linear
layers with B-cos transformations, perform competitively to their respective
standard variants while also yielding explanations that are faithful by design.
However, it has so far been necessary to train these models from scratch, which
is increasingly infeasible in the era of large, pre-trained foundation models.
In this work, inspired by the architectural similarities in standard DNNs and
B-cos networks, we propose 'B-cosification', a novel approach to transform
existing pre-trained models to become inherently interpretable. We perform a
thorough study of design choices to perform this conversion, both for
convolutional neural networks and vision transformers. We find that
B-cosification can yield models that are on par with B-cos models trained from
scratch in terms of interpretability, while often outperforming them in terms
of classification performance at a fraction of the training cost. Subsequently,
we apply B-cosification to a pretrained CLIP model, and show that, even with
limited data and compute cost, we obtain a B-cosified version that is highly
interpretable and competitive on zero shot performance across a variety of
datasets. We release our code and pre-trained model weights at
github.com/shrebox/B-cosification.

Image restoration networks are usually comprised of an encoder and a decoder,
responsible for aggregating image content from noisy, distorted data and to
restore clean, undistorted images, respectively. Data aggregation as well as
high-resolution image generation both usually come at the risk of involving
aliases, i.e.~standard architectures put their ability to reconstruct the model
input in jeopardy to reach high PSNR values on validation data. The price to be
paid is low model robustness. In this work, we show that simply providing
alias-free paths in state-of-the-art reconstruction transformers supports
improved model robustness at low costs on the restoration performance. We do so
by proposing BOA-Restormer, a transformer-based image restoration model that
executes downsampling and upsampling operations partly in the frequency domain
to ensure alias-free paths along the entire model while potentially preserving
all relevant high-frequency information.

In this work, we introduce Scribbles for All, a label and training data
generation algorithm for semantic segmentation trained on scribble labels.
Training or fine-tuning semantic segmentation models with weak supervision has
become an important topic recently and was subject to significant advances in
model quality. In this setting, scribbles are a promising label type to achieve
high quality segmentation results while requiring a much lower annotation
effort than usual pixel-wise dense semantic segmentation annotations. The main
limitation of scribbles as source for weak supervision is the lack of
challenging datasets for scribble segmentation, which hinders the development
of novel methods and conclusive evaluations. To overcome this limitation,
Scribbles for All provides scribble labels for several popular segmentation
datasets and provides an algorithm to automatically generate scribble labels
for any dataset with dense annotations, paving the way for new insights and
model advancements in the field of weakly supervised segmentation. In addition
to providing datasets and algorithm, we evaluate state-of-the-art segmentation
models on our datasets and show that models trained with our synthetic labels
perform competitively with respect to models trained on manual labels. Thus,
our datasets enable state-of-the-art research into methods for scribble-labeled
semantic segmentation. The datasets, scribble generation algorithm, and
baselines are publicly available at github.com/wbkit/Scribbles4All

Low-dimensional embeddings (LDEs) of high-dimensional data are ubiquitous in
science and engineering. They allow us to quickly understand the main
properties of the data, identify outliers and processing errors, and inform the
next steps of data analysis. As such, LDEs have to be faithful to the original
high-dimensional data, i.e., they should represent the relationships that are
encoded in the data, both at a local as well as global scale. The current
generation of LDE approaches focus on reconstructing local distances between
any pair of samples correctly, often out-performing traditional approaches
aiming at all distances. For these approaches, global relationships are,
however, usually strongly distorted, often argued to be an inherent trade-off
between local and global structure learning for embeddings. We suggest a new
perspective on LDE learning, reconstructing angles between data points. We show
that this approach, Mercat, yields good reconstruction across a diverse set of
experiments and metrics, and preserve structures well across all scales.
Compared to existing work, our approach also has a simple formulation,
facilitating future theoretical analysis and algorithmic improvements.

Vision language models (VLMs) have drastically changed the computer vision
model landscape in only a few years, opening an exciting array of new
applications from zero-shot image classification, over to image captioning, and
visual question answering. Unlike pure vision models, they offer an intuitive
way to access visual content through language prompting. The wide applicability
of such models encourages us to ask whether they also align with human vision -
specifically, how far they adopt human-induced visual biases through multimodal
fusion, or whether they simply inherit biases from pure vision models. One
important visual bias is the texture vs. shape bias, or the dominance of local
over global information. In this paper, we study this bias in a wide range of
popular VLMs. Interestingly, we find that VLMs are often more shape-biased than
their vision encoders, indicating that visual biases are modulated to some
extent through text in multimodal models. If text does indeed influence visual
biases, this suggests that we may be able to steer visual biases not just
through visual input but also through language: a hypothesis that we confirm
through extensive experiments. For instance, we are able to steer shape bias
from as low as 49% to as high as 72% through prompting alone. For now, the
strong human bias towards shape (96%) remains out of reach for all tested VLMs.

Deep learning is increasingly relevant in our daily lives, as it simplifies tedious tasks and enhances quality of life across various domains such as entertainment, learning, automatic assistance, and autonomous driving. However, the demand for more data to train models for emerging tasks is increasing dramatically. Deep learning models heavily depend on the quality and quantity of data, necessitating high-quality labeled datasets. Yet, each task requires different types of annotations for training and evaluation, posing challenges in obtaining comprehensive supervision. The acquisition of annotations is not only resource-intensive in terms of time and cost but also introduces biases, such as granularity in classification, where distinctions like specific breeds versus generic categories may arise. Furthermore, the dynamic nature of the world causes the challenge that previously annotated data becomes potentially irrelevant, and new categories and rare occurrences continually emerge, making it impossible to label every aspect of the world.
Therefore, this thesis aims to explore various supervision scenarios to mitigate the need for full supervision and reduce data acquisition costs. Specifically, we investigate learning without labels, referred to as self-supervised and unsupervised methods, to better understand video and image representations. To learn from data without labels, we leverage injected priors such as motion speed, direction, action order in videos, or semantic information granularity to obtain powerful data representations. Further, we study scenarios involving reduced supervision levels. To reduce annotation costs, first, we propose to omit precise annotations for one modality in multimodal learning, namely in text-video and image-video settings, and transfer available knowledge to large copora of video data. Second, we study semi-supervised learning scenarios, where only a subset of annotated data alongside unlabeled data is available, and propose to revisit regularization constraints and improve generalization to unlabeled data. Additionally, we address scenarios where parts of available data is inherently limited due to privacy and security reasons or naturally rare events, which not only restrict annotations but also limit the overall data volume. For these scenarios, we propose methods that carefully balance between previously obtained knowledge and incoming limited data by introducing a calibration method or combining a space reservation technique with orthogonality constraints. Finally, we explore multimodal and unimodal open-world scenarios where the model is asked to generalize beyond the given set of object or action classes. Specifically, we propose a new challenging setting on multimodal egocentric videos and propose an adaptation method for vision-language models to generalize on egocentric domain. Moreover, we study unimodal image recognition in an open-set setting and propose to disentangle open-set detection and image classification tasks that effectively improve generalization in different settings.
In summary, this thesis investigates challenges arising when full supervision for training models is not available. We develop methods to understand learning dynamics and the role of biases in data, while also proposing novel setups to advance training with less supervision.

Reasoning over sports videos for question answering is an important task with
numerous applications, such as player training and information retrieval.
However, this task has not been explored due to the lack of relevant datasets
and the challenging nature it presents. Most datasets for video question
answering (VideoQA) focus mainly on general and coarse-grained understanding of
daily-life videos, which is not applicable to sports scenarios requiring
professional action understanding and fine-grained motion analysis. In this
paper, we introduce the first dataset, named Sports-QA, specifically designed
for the sports VideoQA task. The Sports-QA dataset includes various types of
questions, such as descriptions, chronologies, causalities, and counterfactual
conditions, covering multiple sports. Furthermore, to address the
characteristics of the sports VideoQA task, we propose a new Auto-Focus
Transformer (AFT) capable of automatically focusing on particular scales of
temporal information for question answering. We conduct extensive experiments
on Sports-QA, including baseline studies and the evaluation of different
methods. The results demonstrate that our AFT achieves state-of-the-art
performance.

Despite tremendous progress in the field of text-to-video (T2V) synthesis,
open-sourced T2V diffusion models struggle to generate longer videos with
dynamically varying and evolving content. They tend to synthesize quasi-static
videos, ignoring the necessary visual change-over-time implied in the text
prompt. At the same time, scaling these models to enable longer, more dynamic
video synthesis often remains computationally intractable. To address this
challenge, we introduce the concept of Generative Temporal Nursing (GTN), where
we aim to alter the generative process on the fly during inference to improve
control over the temporal dynamics and enable generation of longer videos. We
propose a method for GTN, dubbed VSTAR, which consists of two key ingredients:
1) Video Synopsis Prompting (VSP) - automatic generation of a video synopsis
based on the original single prompt leveraging LLMs, which gives accurate
textual guidance to different visual states of longer videos, and 2) Temporal
Attention Regularization (TAR) - a regularization technique to refine the
temporal attention units of the pre-trained T2V diffusion models, which enables
control over the video dynamics. We experimentally showcase the superiority of
the proposed approach in generating longer, visually appealing videos over
existing open-sourced T2V models. We additionally analyze the temporal
attention maps realized with and without VSTAR, demonstrating the importance of
applying our method to mitigate neglect of the desired visual change over time.

Deep neural networks are susceptible to adversarial attacks and common
corruptions, which undermine their robustness. In order to enhance model
resilience against such challenges, Adversarial Training (AT) has emerged as a
prominent solution. Nevertheless, adversarial robustness is often attained at
the expense of model fairness during AT, i.e., disparity in class-wise
robustness of the model. While distinctive classes become more robust towards
such adversaries, hard to detect classes suffer. Recently, research has focused
on improving model fairness specifically for perturbed images, overlooking the
accuracy of the most likely non-perturbed data. Additionally, despite their
robustness against the adversaries encountered during model training,
state-of-the-art adversarial trained models have difficulty maintaining
robustness and fairness when confronted with diverse adversarial threats or
common corruptions. In this work, we address the above concerns by introducing
a novel approach called Fair Targeted Adversarial Training (FAIR-TAT). We show
that using targeted adversarial attacks for adversarial training (instead of
untargeted attacks) can allow for more favorable trade-offs with respect to
adversarial fairness. Empirical results validate the efficacy of our approach.

Multiple object tracking in complex scenarios - such as coordinated dance
performances, team sports, or dynamic animal groups - presents unique
challenges. In these settings, objects frequently move in coordinated patterns,
occlude each other, and exhibit long-term dependencies in their trajectories.
However, it remains a key open research question on how to model long-range
dependencies within tracklets, interdependencies among tracklets, and the
associated temporal occlusions. To this end, we introduce Samba, a novel
linear-time set-of-sequences model designed to jointly process multiple
tracklets by synchronizing the multiple selective state-spaces used to model
each tracklet. Samba autoregressively predicts the future track query for each
sequence while maintaining synchronized long-term memory representations across
tracklets. By integrating Samba into a tracking-by-propagation framework, we
propose SambaMOTR, the first tracker effectively addressing the aforementioned
issues, including long-range dependencies, tracklet interdependencies, and
temporal occlusions. Additionally, we introduce an effective technique for
dealing with uncertain observations (MaskObs) and an efficient training recipe
to scale SambaMOTR to longer sequences. By modeling long-range dependencies and
interactions among tracked objects, SambaMOTR implicitly learns to track
objects accurately through occlusions without any hand-crafted heuristics. Our
approach significantly surpasses prior state-of-the-art on the DanceTrack, BFT,
and SportsMOT datasets.

Transformers have become the predominant architecture in foundation models
due to their excellent performance across various domains. However, the
substantial cost of scaling these models remains a significant concern. This
problem arises primarily from their dependence on a fixed number of parameters
within linear projections. When architectural modifications (e.g., channel
dimensions) are introduced, the entire model typically requires retraining from
scratch. As model sizes continue growing, this strategy results in increasingly
high computational costs and becomes unsustainable. To overcome this problem,
we introduce TokenFormer, a natively scalable architecture that leverages the
attention mechanism not only for computations among input tokens but also for
interactions between tokens and model parameters, thereby enhancing
architectural flexibility. By treating model parameters as tokens, we replace
all the linear projections in Transformers with our token-parameter attention
layer, where input tokens act as queries and model parameters as keys and
values. This reformulation allows for progressive and efficient scaling without
necessitating retraining from scratch. Our model scales from 124M to 1.4B
parameters by incrementally adding new key-value parameter pairs, achieving
performance comparable to Transformers trained from scratch while greatly
reducing training costs. Code and models are available at
\url{https://github.com/Haiyang-W/TokenFormer}.

We introduce FaceGPT, a self-supervised learning framework for Large
Vision-Language Models (VLMs) to reason about 3D human faces from images and
text. Typical 3D face reconstruction methods are specialized algorithms that
lack semantic reasoning capabilities. FaceGPT overcomes this limitation by
embedding the parameters of a 3D morphable face model (3DMM) into the token
space of a VLM, enabling the generation of 3D faces from both textual and
visual inputs. FaceGPT is trained in a self-supervised manner as a model-based
autoencoder from in-the-wild images. In particular, the hidden state of LLM is
projected into 3DMM parameters and subsequently rendered as 2D face image to
guide the self-supervised learning process via image-based reconstruction.
Without relying on expensive 3D annotations of human faces, FaceGPT obtains a
detailed understanding about 3D human faces, while preserving the capacity to
understand general user instructions. Our experiments demonstrate that FaceGPT
not only achieves high-quality 3D face reconstructions but also retains the
ability for general-purpose visual instruction following. Furthermore, FaceGPT
learns fully self-supervised to generate 3D faces based on complex textual
inputs, which opens a new direction in human face analysis.

Video Large Language Models (Vid-LLMs) have made remarkable advancements in
comprehending video content for QA dialogue. However, they struggle to extend
this visual understanding to tasks requiring precise temporal localization,
known as Video Temporal Grounding (VTG). To address this gap, we introduce
Number-Prompt (NumPro), a novel method that empowers Vid-LLMs to bridge visual
comprehension with temporal grounding by adding unique numerical identifiers to
each video frame. Treating a video as a sequence of numbered frame images,
NumPro transforms VTG into an intuitive process: flipping through manga panels
in sequence. This allows Vid-LLMs to "read" event timelines, accurately linking
visual content with corresponding temporal information. Our experiments
demonstrate that NumPro significantly boosts VTG performance of top-tier
Vid-LLMs without additional computational cost. Furthermore, fine-tuning on a
NumPro-enhanced dataset defines a new state-of-the-art for VTG, surpassing
previous top-performing methods by up to 6.9\% in mIoU for moment retrieval and
8.5\% in mAP for highlight detection. The code will be available at
github.com/yongliang-wu/NumPro.

Sampling-based decoding strategies have been widely adopted for Large
Language Models (LLMs) in numerous applications, which target a balance between
diversity and quality via temperature tuning and tail truncation (e.g., top-k
and top-p sampling). Considering the high dynamic range of the candidate
next-token given different prefixes, recent studies propose to adaptively
truncate the tail of LLM's predicted distribution. Although improved results
haven been reported with these methods on open-ended text generation tasks, the
results are highly dependent on the curated truncation parameters and exemplar
text. In this paper, we propose a systematic way to estimate the intrinsic
capacity of a truncation sampling method by considering the trade-off between
diversity and risk at each decoding step, based on our collected prefix tree
which preserves the context of a full sentence. Our work provides a
comprehensive comparison between existing truncation sampling methods, as well
as their recommended parameters as a guideline for users.

Deep learning models have proven to be successful in a wide
range of machine learning tasks. Yet, they are often highly sensitive to
perturbations on the input data which can lead to incorrect decisions
with high confidence, hampering their deployment for practical
use-cases. Thus, finding architectures that are (more) robust against
perturbations has received much attention in recent years. Just like the
search for well-performing architectures in terms of clean accuracy,
this usually involves a tedious trial-and-error process with one
additional challenge: the evaluation of a network's robustness is
significantly more expensive than its evaluation for clean accuracy.
Thus, the aim of this paper is to facilitate better streamlined research
on architectural design choices with respect to their impact on
robustness as well as, for example, the evaluation of surrogate measures
for robustness. We therefore borrow one of the most commonly considered
search spaces for neural architecture search for image classification,
NAS-Bench-201, which contains a manageable size of 6466 non-isomorphic
network designs. We evaluate all these networks on a range of common
adversarial attacks and corruption types and introduce a database on
neural architecture design and robustness evaluations. We further
present three exemplary use cases of this dataset, in which we (i)
benchmark robustness measurements based on Jacobian and Hessian matrices
for their robustness predictability, (ii) perform neural architecture
search on robust accuracies, and (iii) provide an initial analysis of
how architectural design choices affect robustness. We find that
carefully crafting the topology of a network can have substantial impact
on its robustness, where networks with the same parameter count range in
mean adversarial robust accuracy from 20%-41%.

Local coherence is essential for long-form text generation models. We identify two important aspects of local coherence within the visual storytelling task: (1) the model needs to represent re-occurrences of characters within the image sequence in order to mention them correctly in the story; (2) character representations should enable us to find instances of the same characters and distinguish different characters. In this paper, we propose a loss function inspired by a linguistic theory of coherence for self-supervised learning for image sequence representations. We further propose combining features from an object and a face detector to construct stronger character features. To evaluate input-output relevance that current reference-based metrics don't measure, we propose a character matching metric to check whether the models generate referring expressions correctly for characters in input image sequences. Experiments on a visual story generation dataset show that our proposed features and loss function are effective for generating more coherent and visually grounded stories.

Human performance capture is a highly important computer vision problem with
many applications in movie production and virtual/augmented reality. Many
previous performance capture approaches either required expensive multi-view
setups or did not recover dense space-time coherent geometry with
frame-to-frame correspondences. We propose a novel deep learning approach for
monocular dense human performance capture. Our method is trained in a weakly
supervised manner based on multi-view supervision completely removing the need
for training data with 3D ground truth annotations. The network architecture is
based on two separate networks that disentangle the task into a pose estimation
and a non-rigid surface deformation step. Extensive qualitative and
quantitative evaluations show that our approach outperforms the state of the
art in terms of quality and robustness. This work is an extended version of
DeepCap where we provide more detailed explanations, comparisons and results as
well as applications.

Minimum cost lifted multicut problem is a generalization of the multicut problem and is a means to optimizing a decomposition of a graph w.r.t. both positive and negative edge costs. Its main advantage is that multicut-based formulations do not require the number of components given a priori; instead, it is deduced from the solution. However, the standard multicut cost function is limited to pairwise relationships between nodes, while several important applications either require or can benefit from a higher-order cost function, i.e. hyper-edges. In this paper, we propose a pseudo-boolean formulation for a multiple model fitting problem. It is based on a formulation of any-order minimum cost lifted multicuts, which allows to partition an undirected graph with pairwise connectivity such as to minimize costs defined over any set of hyper-edges. As the proposed formulation is NP-hard and the branch-and-bound algorithm is too slow in practice, we propose an efficient local search algorithm for inference into resulting problems. We demonstrate versatility and effectiveness of our approach in several applications: geometric multiple model fitting, homography and motion estimation, motion segmentation.

Transformers increasingly dominate the machine learning landscape across many
tasks and domains, which increases the importance for understanding their
outputs. While their attention modules provide partial insight into their inner
workings, the attention scores have been shown to be insufficient for
explaining the models as a whole. To address this, we propose B-cos
transformers, which inherently provide holistic explanations for their
decisions. Specifically, we formulate each model component - such as the
multi-layer perceptrons, attention layers, and the tokenisation module - to be
dynamic linear, which allows us to faithfully summarise the entire transformer
via a single linear transform. We apply our proposed design to Vision
Transformers (ViTs) and show that the resulting models, dubbed Bcos-ViTs, are
highly interpretable and perform competitively to baseline ViTs on ImageNet.
Code will be made available soon.

Zero-shot semantic segmentation (ZS3) aims to segment the novel categories
that have not been seen in the training. Existing works formulate ZS3 as a
pixel-level zero-shot classification problem, and transfer semantic knowledge
from seen classes to unseen ones with the help of language models pre-trained
only with texts. While simple, the pixel-level ZS3 formulation shows the
limited capability to integrate vision-language models that are often
pre-trained with image-text pairs and currently demonstrate great potential for
vision tasks. Inspired by the observation that humans often perform
segment-level semantic labeling, we propose to decouple the ZS3 into two
sub-tasks: 1) a class-agnostic grouping task to group the pixels into segments.
2) a zero-shot classification task on segments. The former sub-task does not
involve category information and can be directly transferred to group pixels
for unseen classes. The latter subtask performs at segment-level and provides a
natural way to leverage large-scale vision-language models pre-trained with
image-text pairs (e.g. CLIP) for ZS3. Based on the decoupling formulation, we
propose a simple and effective zero-shot semantic segmentation model, called
ZegFormer, which outperforms the previous methods on ZS3 standard benchmarks by
large margins, e.g., 35 points on the PASCAL VOC and 3 points on the COCO-Stuff
in terms of mIoU for unseen classes. Code will be released at
github.com/dingjiansw101/ZegFormer.

In this paper, we propose a novel co-learning framework (CoSSL) with
decoupled representation learning and classifier learning for imbalanced SSL.
To handle the data imbalance, we devise Tail-class Feature Enhancement (TFE)
for classifier learning. Furthermore, the current evaluation protocol for
imbalanced SSL focuses only on balanced test sets, which has limited
practicality in real-world scenarios. Therefore, we further conduct a
comprehensive evaluation under various shifted test distributions. In
experiments, we show that our approach outperforms other methods over a large
range of shifted distributions, achieving state-of-the-art performance on
benchmark datasets ranging from CIFAR-10, CIFAR-100, ImageNet, to Food-101. Our
code will be made publicly available.

As acquiring pixel-wise annotations of real-world images for semantic
segmentation is a costly process, a model can instead be trained with more
accessible synthetic data and adapted to real images without requiring their
annotations. This process is studied in unsupervised domain adaptation (UDA).
Even though a large number of methods propose new adaptation strategies, they
are mostly based on outdated network architectures. As the influence of recent
network architectures has not been systematically studied, we first benchmark
different network architectures for UDA and then propose a novel UDA method,
DAFormer, based on the benchmark results. The DAFormer network consists of a
Transformer encoder and a multi-level context-aware feature fusion decoder. It
is enabled by three simple but crucial training strategies to stabilize the
training and to avoid overfitting DAFormer to the source domain: While the Rare
Class Sampling on the source domain improves the quality of pseudo-labels by
mitigating the confirmation bias of self-training towards common classes, the
Thing-Class ImageNet Feature Distance and a learning rate warmup promote
feature transfer from ImageNet pretraining. DAFormer significantly improves the
state-of-the-art performance by 10.8 mIoU for GTA->Cityscapes and 5.4 mIoU for
Synthia->Cityscapes and enables learning even difficult classes such as train,
bus, and truck well. The implementation is available at
github.com/lhoyer/DAFormer.

Although considerable progress has been made in semantic scene understanding
under clear weather, it is still a tough problem under adverse weather
conditions, such as dense fog, due to the uncertainty caused by imperfect
observations. Besides, difficulties in collecting and labeling foggy images
hinder the progress of this field. Considering the success in semantic scene
understanding under clear weather, we think it is reasonable to transfer
knowledge learned from clear images to the foggy domain. As such, the problem
becomes to bridge the domain gap between clear images and foggy images. Unlike
previous methods that mainly focus on closing the domain gap caused by fog --
defogging the foggy images or fogging the clear images, we propose to alleviate
the domain gap by considering fog influence and style variation simultaneously.
The motivation is based on our finding that the style-related gap and the
fog-related gap can be divided and closed respectively, by adding an
intermediate domain. Thus, we propose a new pipeline to cumulatively adapt
style, fog and the dual-factor (style and fog). Specifically, we devise a
unified framework to disentangle the style factor and the fog factor
separately, and then the dual-factor from images in different domains.
Furthermore, we collaborate the disentanglement of three factors with a novel
cumulative loss to thoroughly disentangle these three factors. Our method
achieves the state-of-the-art performance on three benchmarks and shows
generalization ability in rainy and snowy scenes.

Multi-Camera Multi-Object Tracking is currently drawing attention in the
computer vision field due to its superior performance in real-world
applications such as video surveillance with crowded scenes or in vast space.
In this work, we propose a mathematically elegant multi-camera multiple object
tracking approach based on a spatial-temporal lifted multicut formulation. Our
model utilizes state-of-the-art tracklets produced by single-camera trackers as
proposals. As these tracklets may contain ID-Switch errors, we refine them
through a novel pre-clustering obtained from 3D geometry projections. As a
result, we derive a better tracking graph without ID switches and more precise
affinity costs for the data association phase. Tracklets are then matched to
multi-camera trajectories by solving a global lifted multicut formulation that
incorporates short and long-range temporal interactions on tracklets located in
the same camera as well as inter-camera ones. Experimental results on the
WildTrack dataset yield near-perfect result, outperforming state-of-the-art
trackers on Campus while being on par on the PETS-09 dataset. We will make our
implementations available upon acceptance of the paper.

3D human motion capture from monocular RGB images respecting interactions of
a subject with complex and possibly deformable environments is a very
challenging, ill-posed and under-explored problem. Existing methods address it
only weakly and do not model possible surface deformations often occurring when
humans interact with scene surfaces. In contrast, this paper proposes
MoCapDeform, i.e., a new framework for monocular 3D human motion capture that
is the first to explicitly model non-rigid deformations of a 3D scene for
improved 3D human pose estimation and deformable environment reconstruction.
MoCapDeform accepts a monocular RGB video and a 3D scene mesh aligned in the
camera space. It first localises a subject in the input monocular video along
with dense contact labels using a new raycasting based strategy. Next, our
human-environment interaction constraints are leveraged to jointly optimise
global 3D human poses and non-rigid surface deformations. MoCapDeform achieves
superior accuracy than competing methods on several datasets, including our
newly recorded one with deforming background scenes.

The minimum cost multicut problem is the NP-hard/APX-hard combinatorial
optimization problem of partitioning a real-valued edge-weighted graph such as
to minimize the total cost of the partition. While graph convolutional neural
networks (GNN) have proven to be promising in the context of combinatorial
optimization, most of them are only tailored to or tested on positive-valued
edge weights, i.e. they do not comply to the nature of the multicut problem. We
therefore adapt various GNN architectures including Graph Convolutional
Networks, Signed Graph Convolutional Networks and Graph Isomorphic Networks to
facilitate the efficient encoding of real-valued edge costs. Moreover, we
employ a reformulation of the multicut ILP constraints to a polynomial program
as loss function that allows to learn feasible multicut solutions in a scalable
way. Thus, we provide the first approach towards end-to-end trainable
multicuts. Our findings support that GNN approaches can produce good solutions
in practice while providing lower computation times and largely improved
scalability compared to LP solvers and optimized heuristics, especially when
considering large instances.

The Minimum Cost Multicut Problem (MP) is a popular way for obtaining a graph
decomposition by optimizing binary edge labels over edge costs. While the
formulation of a MP from independently estimated costs per edge is highly
flexible and intuitive, solving the MP is NP-hard and time-expensive. As a
remedy, recent work proposed to predict edge probabilities with awareness to
potential conflicts by incorporating cycle constraints in the prediction
process. We argue that such formulation, while providing a first step towards
end-to-end learnable edge weights, is suboptimal, since it is built upon a
loose relaxation of the MP. We therefore propose an adaptive CRF that allows to
progressively consider more violated constraints and, in consequence, to issue
solutions with higher validity. Experiments on the BSDS500 benchmark for
natural image segmentation as well as on electron microscopic recordings show
that our approach yields more precise edge detection and image segmentation.

Planning an optimal route in a complex environment requires efficient
reasoning about the surrounding scene. While human drivers prioritize important
objects and ignore details not relevant to the decision, learning-based
planners typically extract features from dense, high-dimensional grid
representations containing all vehicle and road context information. In this
paper, we propose PlanT, a novel approach for planning in the context of
self-driving that uses a standard transformer architecture. PlanT is based on
imitation learning with a compact object-level input representation. On the
Longest6 benchmark for CARLA, PlanT outperforms all prior methods (matching the
driving score of the expert) while being 5.3x faster than equivalent
pixel-based planning baselines during inference. Combining PlanT with an
off-the-shelf perception module provides a sensor-based driving system that is
more than 10 points better in terms of driving score than the existing state of
the art. Furthermore, we propose an evaluation protocol to quantify the ability
of planners to identify relevant objects, providing insights regarding their
decision-making. Our results indicate that PlanT can focus on the most relevant
object in the scene, even when this object is geometrically distant.

Semi-supervised learning (SSL) has shown great promise in leveraging
unlabeled data to improve model performance. While standard SSL assumes uniform
data distribution, we consider a more realistic and challenging setting called
imbalanced SSL, where imbalanced class distributions occur in both labeled and
unlabeled data. Although there are existing endeavors to tackle this challenge,
their performance degenerates when facing severe imbalance since they can not
reduce the class imbalance sufficiently and effectively. In this paper, we
study a simple yet overlooked baseline -- SimiS -- which tackles data imbalance
by simply supplementing labeled data with pseudo-labels, according to the
difference in class distribution from the most frequent class. Such a simple
baseline turns out to be highly effective in reducing class imbalance. It
outperforms existing methods by a significant margin, e.g., 12.8%, 13.6%, and
16.7% over previous SOTA on CIFAR100-LT, FOOD101-LT, and ImageNet127
respectively. The reduced imbalance results in faster convergence and better
pseudo-label accuracy of SimiS. The simplicity of our method also makes it
possible to be combined with other re-balancing techniques to improve the
performance further. Moreover, our method shows great robustness to a wide
range of data distributions, which holds enormous potential in practice. Code
will be publicly available.

Unintentional actions are rare occurrences that are difficult to define
precisely and that are highly dependent on the temporal context of the action.
In this work, we explore such actions and seek to identify the points in videos
where the actions transition from intentional to unintentional. We propose a
multi-stage framework that exploits inherent biases such as motion speed,
motion direction, and order to recognize unintentional actions. To enhance
representations via self-supervised training for the task of unintentional
action recognition we propose temporal transformations, called Temporal
Transformations of Inherent Biases of Unintentional Actions (T2IBUA). The
multi-stage approach models the temporal information on both the level of
individual frames and full clips. These enhanced representations show strong
performance for unintentional action recognition tasks. We provide an extensive
ablation study of our framework and report results that significantly improve
over the state-of-the-art.

Improving model's generalizability against domain shifts is crucial,
especially for safety-critical applications such as autonomous driving.
Real-world domain styles can vary substantially due to environment changes and
sensor noises, but deep models only know the training domain style. Such domain
style gap impedes model generalization on diverse real-world domains. Our
proposed Normalization Perturbation (NP) can effectively overcome this domain
style overfitting problem. We observe that this problem is mainly caused by the
biased distribution of low-level features learned in shallow CNN layers. Thus,
we propose to perturb the channel statistics of source domain features to
synthesize various latent styles, so that the trained deep model can perceive
diverse potential domains and generalizes well even without observations of
target domain data in training. We further explore the style-sensitive channels
for effective style synthesis. Normalization Perturbation only relies on a
single source domain and is surprisingly effective and extremely easy to
implement. Extensive experiments verify the effectiveness of our method for
generalizing models under real-world domain shifts.

In everyday lives, humans naturally modify the surrounding environment
through interactions, e.g., moving a chair to sit on it. To reproduce such
interactions in virtual spaces (e.g., metaverse), we need to be able to capture
and model them, including changes in the scene geometry, ideally from
ego-centric input alone (head camera and body-worn inertial sensors). This is
an extremely hard problem, especially since the object/scene might not be
visible from the head camera (e.g., a human not looking at a chair while
sitting down, or not looking at the door handle while opening a door). In this
paper, we present HOPS, the first method to capture interactions such as
dragging objects and opening doors from ego-centric data alone. Central to our
method is reasoning about human-object interactions, allowing to track objects
even when they are not visible from the head camera. HOPS localizes and
registers both the human and the dynamic object in a pre-scanned static scene.
HOPS is an important first step towards advanced AR/VR applications based on
immersive virtual universes, and can provide human-centric training data to
teach machines to interact with their surroundings. The supplementary video,
data, and code will be available on our project page at
virtualhumans.mpi-inf.mpg.de/hops/

This paper introduces DGNet, a novel deep framework that exploits object
gradient supervision for camouflaged object detection (COD). It decouples the
task into two connected branches, i.e., a context and a texture encoder. The
essential connection is the gradient-induced transition, representing a soft
grouping between context and texture features. Benefiting from the simple but
efficient framework, DGNet outperforms existing state-of-the-art COD models by
a large margin. Notably, our efficient version, DGNet-S, runs in real-time (80
fps) and achieves comparable results to the cutting-edge model
JCSOD-CVPR$_{21}$ with only 6.82% parameters. Application results also show
that the proposed DGNet performs well in polyp segmentation, defect detection,
and transparent object segmentation tasks. Codes will be made available at
github.com/GewelsJI/DGNet.

In this report, we present the 1st place solution for motion prediction track
in 2022 Waymo Open Dataset Challenges. We propose a novel Motion Transformer
framework for multimodal motion prediction, which introduces a small set of
novel motion query pairs for generating better multimodal future trajectories
by jointly performing the intention localization and iterative motion
refinement. A simple model ensemble strategy with non-maximum-suppression is
adopted to further boost the final performance. Our approach achieves the 1st
place on the motion prediction leaderboard of 2022 Waymo Open Dataset
Challenges, outperforming other methods with remarkable margins. Code will be
available at github.com/sshaoshuai/MTR.

Deep learning is becoming increasingly relevant for many high-stakes applications such as autonomous driving or medical diagnosis where wrong decisions can have massive impact on human lives. Unfortunately, deep neural networks are typically assessed solely based on generalization, e.g., accuracy on a fixed test set. However, this is clearly insufficient for safe deployment as potential malicious actors and distribution shifts or the effects of quantization and unreliable hardware are disregarded. Thus, recent work additionally evaluates performance on potentially manipulated or corrupted inputs as well as after quantization and deployment on specialized hardware. In such settings, it is also important to obtain reasonable estimates of the model's confidence alongside its predictions. This thesis studies robustness and uncertainty estimation in deep learning along three main directions: First, we consider so-called adversarial examples, slightly perturbed inputs causing severe drops in accuracy. Second, we study weight perturbations, focusing particularly on bit errors in quantized weights. This is relevant for deploying models on special-purpose hardware for efficient inference, so-called accelerators. Finally, we address uncertainty estimation to improve robustness and provide meaningful statistical performance guarantees for safe deployment. In detail, we study the existence of adversarial examples with respect to the underlying data manifold. In this context, we also investigate adversarial training which improves robustness by augmenting training with adversarial examples at the cost of reduced accuracy. We show that regular adversarial examples leave the data manifold in an almost orthogonal direction. While we find no inherent trade-off between robustness and accuracy, this contributes to a higher sample complexity as well as severe overfitting of adversarial training. Using a novel measure of flatness in the robust loss landscape with respect to weight changes, we also show that robust overfitting is caused by converging to particularly sharp minima. In fact, we find a clear correlation between flatness and good robust generalization. Further, we study random and adversarial bit errors in quantized weights. In accelerators, random bit errors occur in the memory when reducing voltage with the goal of improving energy-efficiency. Here, we consider a robust quantization scheme, use weight clipping as regularization and perform random bit error training to improve bit error robustness, allowing considerable energy savings without requiring hardware changes. In contrast, adversarial bit errors are maliciously introduced through hardware- or software-based attacks on the memory, with severe consequences on performance. We propose a novel adversarial bit error attack to study this threat and use adversarial bit error training to improve robustness and thereby also the accelerator's security. Finally, we view robustness in the context of uncertainty estimation. By encouraging low-confidence predictions on adversarial examples, our confidence-calibrated adversarial training successfully rejects adversarial, corrupted as well as out-of-distribution examples at test time. Thereby, we are also able to improve the robustness-accuracy trade-off compared to regular adversarial training. However, even robust models do not provide any guarantee for safe deployment. To address this problem, conformal prediction allows the model to predict confidence sets with user-specified guarantee of including the true label. Unfortunately, as conformal prediction is usually applied after training, the model is trained without taking this calibration step into account. To address this limitation, we propose conformal training which allows training conformal predictors end-to-end with the underlying model. This not only improves the obtained uncertainty estimates but also enables optimizing application-specific objectives without losing the provided guarantee. Besides our work on robustness or uncertainty, we also address the problem of 3D shape completion of partially observed point clouds. Specifically, we consider an autonomous driving or robotics setting where vehicles are commonly equipped with LiDAR or depth sensors and obtaining a complete 3D representation of the environment is crucial. However, ground truth shapes that are essential for applying deep learning techniques are extremely difficult to obtain. Thus, we propose a weakly-supervised approach that can be trained on the incomplete point clouds while offering efficient inference. In summary, this thesis contributes to our understanding of robustness against both input and weight perturbations. To this end, we also develop methods to improve robustness alongside uncertainty estimation for safe deployment of deep learning methods in high-stakes applications. In the particular context of autonomous driving, we also address 3D shape completion of sparse point clouds.

Structured prediction problems are one of the fundamental tools in machine
learning. In order to facilitate algorithm development for their numerical
solution, we collect in one place a large number of datasets in easy to read
formats for a diverse set of problem classes. We provide archival links to
datasets, description of the considered problems and problem formats, and a
short summary of problem characteristics including size, number of instances
etc. For reference we also give a non-exhaustive selection of algorithms
proposed in the literature for their solution. We hope that this central
repository will make benchmarking and comparison to established works easier.
We welcome submission of interesting new datasets and algorithms for inclusion
in our archive.

Modern deep learning architecture utilize batch normalization (BN) to
stabilize training and improve accuracy. It has been shown that the BN layers
alone are surprisingly expressive. In the context of robustness against
adversarial examples, however, BN is argued to increase vulnerability. That is,
BN helps to learn fragile features. Nevertheless, BN is still used in
adversarial training, which is the de-facto standard to learn robust features.
In order to shed light on the role of BN in adversarial training, we
investigate to what extent the expressiveness of BN can be used to robustify
fragile features in comparison to random features. On CIFAR10, we find that
adversarially fine-tuning just the BN layers can result in non-trivial
adversarial robustness. Adversarially training only the BN layers from scratch,
in contrast, is not able to convey meaningful adversarial robustness. Our
results indicate that fragile features can be used to learn models with
moderate adversarial robustness, while random features cannot

Current efficient LiDAR-based detection frameworks are lacking in exploiting
object relations, which naturally present in both spatial and temporal manners.
To this end, we introduce a simple, efficient, and effective two-stage
detector, termed as Ret3D. At the core of Ret3D is the utilization of novel
intra-frame and inter-frame relation modules to capture the spatial and
temporal relations accordingly. More Specifically, intra-frame relation module
(IntraRM) encapsulates the intra-frame objects into a sparse graph and thus
allows us to refine the object features through efficient message passing. On
the other hand, inter-frame relation module (InterRM) densely connects each
object in its corresponding tracked sequences dynamically, and leverages such
temporal information to further enhance its representations efficiently through
a lightweight transformer network. We instantiate our novel designs of IntraRM
and InterRM with general center-based or anchor-based detectors and evaluate
them on Waymo Open Dataset (WOD). With negligible extra overhead, Ret3D
achieves the state-of-the-art performance, being 5.5% and 3.2% higher than the
recent competitor in terms of the LEVEL 1 and LEVEL 2 mAPH metrics on vehicle
detection, respectively.

We present TOCH, a method for refining incorrect 3D hand-object interaction
sequences using a data prior. Existing hand trackers, especially those that
rely on very few cameras, often produce visually unrealistic results with
hand-object intersection or missing contacts. Although correcting such errors
requires reasoning about temporal aspects of interaction, most previous work
focus on static grasps and contacts. The core of our method are TOCH fields, a
novel spatio-temporal representation for modeling correspondences between hands
and objects during interaction. The key component is a point-wise
object-centric representation which encodes the hand position relative to the
object. Leveraging this novel representation, we learn a latent manifold of
plausible TOCH fields with a temporal denoising auto-encoder. Experiments
demonstrate that TOCH outperforms state-of-the-art (SOTA) 3D hand-object
interaction models, which are limited to static grasps and contacts. More
importantly, our method produces smooth interactions even before and after
contact. Using a single trained TOCH model, we quantitatively and qualitatively
demonstrate its usefulness for 1) correcting erroneous reconstruction results
from off-the-shelf RGB/RGB-D hand-object reconstruction methods, 2) de-noising,
and 3) grasp transfer across objects. We will release our code and trained
model on our project page at virtualhumans.mpi-inf.mpg.de/toch/

Skeleton-based action recognition aims to predict human actions given human
joint coordinates with skeletal interconnections. To model such off-grid data
points and their co-occurrences, Transformer-based formulations would be a
natural choice. However, Transformers still lag behind state-of-the-art methods
using graph convolutional networks (GCNs). Transformers assume that the input
is permutation-invariant and homogeneous (partially alleviated by positional
encoding), which ignores an important characteristic of skeleton data, i.e.,
bone connectivity. Furthermore, each type of body joint has a clear physical
meaning in human motion, i.e., motion retains an intrinsic relationship
regardless of the joint coordinates, which is not explored in Transformers. In
fact, certain re-occurring groups of body joints are often involved in specific
actions, such as the subconscious hand movement for keeping balance. Vanilla
attention is incapable of describing such underlying relations that are
persistent and beyond pair-wise. In this work, we aim to exploit these unique
aspects of skeleton data to close the performance gap between Transformers and
GCNs. Specifically, we propose a new self-attention (SA) extension, named
Hypergraph Self-Attention (HyperSA), to incorporate inherently higher-order
relations into the model. The K-hop relative positional embeddings are also
employed to take bone connectivity into account. We name the resulting model
Hyperformer, and it achieves comparable or better performance w.r.t. accuracy
and efficiency than state-of-the-art GCN architectures on NTU RGB+D, NTU RGB+D
120, and Northwestern-UCLA datasets. On the largest NTU RGB+D 120 dataset, the
significantly improved performance reached by our Hyperformer demonstrates the
underestimated potential of Transformer models in this field.

Deep neural network (DNN) accelerators received considerable attention in
past years due to saved energy compared to mainstream hardware. Low-voltage
operation of DNN accelerators allows to further reduce energy consumption
significantly, however, causes bit-level failures in the memory storing the
quantized DNN weights. In this paper, we show that a combination of robust
fixed-point quantization, weight clipping, and random bit error training
(RandBET) improves robustness against random bit errors in (quantized) DNN
weights significantly. This leads to high energy savings from both low-voltage
operation as well as low-precision quantization. Our approach generalizes
across operating voltages and accelerators, as demonstrated on bit errors from
profiled SRAM arrays. We also discuss why weight clipping alone is already a
quite effective way to achieve robustness against bit errors. Moreover, we
specifically discuss the involved trade-offs regarding accuracy, robustness and
precision: Without losing more than 1% in accuracy compared to a normally
trained 8-bit DNN, we can reduce energy consumption on CIFAR-10 by 20%. Higher
energy savings of, e.g., 30%, are possible at the cost of 2.5% accuracy, even
for 4-bit DNNs.

We present a massively parallel Lagrange decomposition method for solving 0-1
integer linear programs occurring in structured prediction. We propose a new
iterative update scheme for solving the Lagrangean dual and a perturbation
technique for decoding primal solutions. For representing subproblems we follow
Lange et al. (2021) and use binary decision diagrams (BDDs). Our primal and
dual algorithms require little synchronization between subproblems and
optimization over BDDs needs only elementary operations without complicated
control flow. This allows us to exploit the parallelism offered by GPUs for all
components of our method. We present experimental results on combinatorial
problems from MAP inference for Markov Random Fields, quadratic assignment and
cell tracking for developmental biology. Our highly parallel GPU implementation
improves upon the running times of the algorithms from Lange et al. (2021) by
up to an order of magnitude. In particular, we come close to or outperform some
state-of-the-art specialized heuristics while being problem agnostic.

Explaining the decision of a multi-modal decision-maker requires to determine
the evidence from both modalities. Recent advances in XAI provide explanations
for models trained on still images. However, when it comes to modeling multiple
sensory modalities in a dynamic world, it remains underexplored how to
demystify the mysterious dynamics of a complex multi-modal model. In this work,
we take a crucial step forward and explore learnable explanations for
audio-visual recognition. Specifically, we propose a novel space-time attention
network that uncovers the synergistic dynamics of audio and visual data over
both space and time. Our model is capable of predicting the audio-visual video
events, while justifying its decision by localizing where the relevant visual
cues appear, and when the predicted sounds occur in videos. We benchmark our
model on three audio-visual video event datasets, comparing extensively to
multiple recent multi-modal representation learners and intrinsic explanation
models. Experimental results demonstrate the clear superior performance of our
model over the existing methods on audio-visual video event recognition.
Moreover, we conduct an in-depth study to analyze the explainability of our
model based on robustness analysis via perturbation tests and pointing games
using human annotations.

Traditional domain adaptation addresses the task of adapting a model to a
novel target domain under limited or no additional supervision. While tackling
the input domain gap, the standard domain adaptation settings assume no domain
change in the output space. In semantic prediction tasks, different datasets
are often labeled according to different semantic taxonomies. In many
real-world settings, the target domain task requires a different taxonomy than
the one imposed by the source domain. We therefore introduce the more general
taxonomy adaptive domain adaptation (TADA) problem, allowing for inconsistent
taxonomies between the two domains. We further propose an approach that jointly
addresses the image-level and label-level domain adaptation. On the
label-level, we employ a bilateral mixed sampling strategy to augment the
target domain, and a relabelling method to unify and align the label spaces. We
address the image-level domain gap by proposing an uncertainty-rectified
contrastive learning method, leading to more domain-invariant and class
discriminative features. We extensively evaluate the effectiveness of our
framework under different TADA settings: open taxonomy, coarse-to-fine
taxonomy, and partially-overlapping taxonomy. Our framework outperforms
previous state-of-the-art by a large margin, while capable of adapting to
target taxonomies.

Compositional Zero-Shot learning (CZSL) aims to recognize unseen compositions
of state and object visual primitives seen during training. A problem with
standard CZSL is the assumption of knowing which unseen compositions will be
available at test time. In this work, we overcome this assumption operating on
the open world setting, where no limit is imposed on the compositional space at
test time, and the search space contains a large number of unseen compositions.
To address this problem, we propose a new approach, Compositional Cosine Graph
Embeddings (Co-CGE), based on two principles. First, Co-CGE models the
dependency between states, objects and their compositions through a graph
convolutional neural network. The graph propagates information from seen to
unseen concepts, improving their representations. Second, since not all unseen
compositions are equally feasible, and less feasible ones may damage the
learned representations, Co-CGE estimates a feasibility score for each unseen
composition, using the scores as margins in a cosine similarity-based loss and
as weights in the adjacency matrix of the graphs. Experiments show that our
approach achieves state-of-the-art performances in standard CZSL while
outperforming previous methods in the open world scenario.

Abstract
Humans are at the centre of a significant amount of research in computer vision.
Endowing machines with the ability to perceive people from visual data is an immense
scientific challenge with a high degree of direct practical relevance. Success in automatic
perception can be measured at different levels of abstraction, and this will depend on
which intelligent behaviour we are trying to replicate: the ability to localise persons in
an image or in the environment, understanding how persons are moving at the skeleton
and at the surface level, interpreting their interactions with the environment including
with other people, and perhaps even anticipating future actions. In this thesis we tackle
different sub-problems of the broad research area referred to as "looking at people",
aiming to perceive humans in images at different levels of granularity.
We start with bounding box-level pedestrian detection: We present a retrospective
analysis of methods published in the decade preceding our work, identifying various
strands of research that have advanced the state of the art. With quantitative exper-
iments, we demonstrate the critical role of developing better feature representations
and having the right training distribution. We then contribute two methods based
on the insights derived from our analysis: one that combines the strongest aspects of
past detectors and another that focuses purely on learning representations. The latter
method outperforms more complicated approaches, especially those based on hand-
crafted features. We conclude our work on pedestrian detection with a forward-looking
analysis that maps out potential avenues for future research.
We then turn to pixel-level methods: Perceiving humans requires us to both separate
them precisely from the background and identify their surroundings. To this end, we
introduce Cityscapes, a large-scale dataset for street scene understanding. This has since
established itself as a go-to benchmark for segmentation and detection. We additionally
develop methods that relax the requirement for expensive pixel-level annotations, focusing
on the task of boundary detection, i.e. identifying the outlines of relevant objects and
surfaces. Next, we make the jump from pixels to 3D surfaces, from localising and
labelling to fine-grained spatial understanding. We contribute a method for recovering
3D human shape and pose, which marries the advantages of learning-based and model-
based approaches.
We conclude the thesis with a detailed discussion of benchmarking practices in
computer vision. Among other things, we argue that the design of future datasets
should be driven by the general goal of combinatorial robustness besides task-specific
considerations.

Most learning methods for 3D data (point clouds, meshes) suffer significant
performance drops when the data is not carefully aligned to a canonical
orientation. Aligning real world 3D data collected from different sources is
non-trivial and requires manual intervention. In this paper, we propose the
Adjoint Rigid Transform (ART) Network, a neural module which can be integrated
with a variety of 3D networks to significantly boost their performance. ART
learns to rotate input shapes to a learned canonical orientation, which is
crucial for a lot of tasks such as shape reconstruction, interpolation,
non-rigid registration, and latent disentanglement. ART achieves this with
self-supervision and a rotation equivariance constraint on predicted rotations.
The remarkable result is that with only self-supervision, ART facilitates
learning a unique canonical orientation for both rigid and nonrigid shapes,
which leads to a notable boost in performance of aforementioned tasks. We will
release our code and pre-trained models for further research.

Modern approaches to pose and body shape estimation have recently achieved
strong performance even under challenging real-world conditions. Even from a
single image of a clothed person, a realistic looking body shape can be
inferred that captures a users' weight group and body shape type well. This
opens up a whole spectrum of applications -- in particular in fashion -- where
virtual try-on and recommendation systems can make use of these new and
automatized cues. However, a realistic depiction of the undressed body is
regarded highly private and therefore might not be consented by most people.
Hence, we ask if the automatic extraction of such information can be
effectively evaded. While adversarial perturbations have been shown to be
effective for manipulating the output of machine learning models -- in
particular, end-to-end deep learning approaches -- state of the art shape
estimation methods are composed of multiple stages. We perform the first
investigation of different strategies that can be used to effectively
manipulate the automatic shape estimation while preserving the overall
appearance of the original image.

Current datasets for video-based person re-identification (re-ID) do not
include structural knowledge in form of human pose annotations for the persons
of interest. Nonetheless, pose information is very helpful to disentangle
useful feature information from background or occlusion noise. Especially
real-world scenarios, such as surveillance, contain a lot of occlusions in
human crowds or by obstacles. On the other hand, video-based person re-ID can
benefit other tasks such as multi-person pose tracking in terms of robust
feature matching. For that reason, we present PoseTrackReID, a large-scale
dataset for multi-person pose tracking and video-based person re-ID. With
PoseTrackReID, we want to bridge the gap between person re-ID and multi-person
pose tracking. Additionally, this dataset provides a good benchmark for current
state-of-the-art methods on multi-frame person re-ID.

Intuitively, image classification should profit from using spatial
information. Recent work, however, suggests that this might be overrated in
standard CNNs. In this paper, we are pushing the envelope and aim to further
investigate the reliance on spatial information. We propose spatial shuffling
and GAP+FC to destroy spatial information during both training and testing
phases. Interestingly, we observe that spatial information can be deleted from
later layers with small performance drops, which indicates spatial information
at later layers is not necessary for good performance. For example, test
accuracy of VGG-16 only drops by 0.03% and 2.66% with spatial information
completely removed from the last 30% and 53% layers on CIFAR100, respectively.
Evaluation on several object recognition datasets (CIFAR100, Small-ImageNet,
ImageNet) with a wide range of CNN architectures (VGG16, ResNet50, ResNet152)
shows an overall consistent pattern.

Modern deep learning has enabled amazing developments of computer vision in recent years (Hinton and Salakhutdinov, 2006; Krizhevsky et al., 2012). As a fundamental task, semantic segmentation aims to predict class labels for each pixel of images, which empowers machines perception of the visual world. In spite of recent successes of fully convolutional networks (Long etal., 2015), several challenges remain to be addressed. In this thesis, we focus on this topic, under different kinds of input formats and various types of scenes. Specifically, our study contains two aspects: (1) Data-driven neural modules for improved performance. (2) Leverage of datasets w.r.t.training systems with higher performances and better data privacy guarantees. In the first part of this thesis, we improve semantic segmentation by designing new modules which are compatible with existing architectures. First, we develop a spatio-temporal data-driven pooling, which brings additional information of data (i.e. superpixels) into neural networks, benefiting the training of neural networks as well as the inference on novel data. We investigate our approach in RGB-D videos for segmenting indoor scenes, where depth provides complementary cues to colors and our model performs particularly well. Second, we design learnable dilated convolutions, which are the extension of standard dilated convolutions, whose dilation factors (Yu and Koltun, 2016) need to be carefully determined by hand to obtain decent performance. We present a method to learn dilation factors together with filter weights of convolutions to avoid a complicated search of dilation factors. We explore extensive studies on challenging street scenes, across various baselines with different complexity as well as several datasets at varying image resolutions. In the second part, we investigate how to utilize expensive training data. First, we start from the generative modelling and study the network architectures and the learning pipeline for generating multiple examples. We aim to improve the diversity of generated examples but also to preserve the comparable quality of the examples. Second, we develop a generative model for synthesizing features of a network. With a mixture of real images and synthetic features, we are able to train a segmentation model with better generalization capability. Our approach is evaluated on different scene parsing tasks to demonstrate the effectiveness of the proposed method. Finally, we study membership inference on the semantic segmentation task. We propose the first membership inference attack system against black-box semantic segmentation models, that tries to infer if a data pair is used as training data or not. From our observations, information on training data is indeed leaking. To mitigate the leakage, we leverage our synthetic features to perform prediction obfuscations, reducing the posterior distribution gaps between a training and a testing set. Consequently, our study provides not only an approach for detecting illegal use of data, but also the foundations for a safer use of semantic segmentation models.

Automatic detection of emergent leaders in small groups from nonverbal
behaviour is a growing research topic in social signal processing but existing
methods were evaluated on single datasets -- an unrealistic assumption for
real-world applications in which systems are required to also work in settings
unseen at training time. It therefore remains unclear whether current methods
for emergent leadership detection generalise to similar but new settings and to
which extent. To overcome this limitation, we are the first to study a
cross-dataset evaluation setting for the emergent leadership detection task. We
provide evaluations for within- and cross-dataset prediction using two current
datasets (PAVIS and MPIIGroupInteraction), as well as an investigation on the
robustness of commonly used feature channels (visual focus of attention, body
pose, facial action units, speaking activity) and online prediction in the
cross-dataset setting. Our evaluations show that using pose and eye contact
based features, cross-dataset prediction is possible with an accuracy of 0.68,
as such providing another important piece of the puzzle towards emergent
leadership detection in the real world.

When labeled training data is scarce, a promising data augmentation approach is to generate visual features of unknown classes using their attributes. To learn the class conditional distribution of CNN features, these models rely on pairs of image features and class attributes. Hence, they can not make use of the abundance of unlabeled data samples. In this paper, we tackle any-shot learning problems i.e. zero-shot and few-shot, in a unified feature generating framework that operates in both inductive and transductive learning settings. We develop a conditional generative model that combines the strength of VAE and GANs and in addition, via an unconditional discriminator, learns the marginal feature distribution of unlabeled images. We empirically show that our model learns highly discriminative CNN features for five datasets, i.e. CUB, SUN, AWA and ImageNet, and establish a new state-of-the-art in any-shot learning, i.e. inductive and transductive (generalized) zero- and few-shot learning settings. We also demonstrate that our learned features are interpretable: we visualize them by inverting them back to the pixel space and we explain them by generating textual arguments of why they are associated with a certain label.

When labeled training data is scarce, a promising data augmentation approach is to generate visual features of unknown classes using their attributes. To learn the class conditional distribution of CNN features, these models rely on pairs of image features and class attributes. Hence, they can not make use of the abundance of unlabeled data samples. In this paper, we tackle any-shot learning problems i.e. zero-shot and few-shot, in a unified feature generating framework that operates in both inductive and transductive learning settings. We develop a conditional generative model that combines the strength of VAE and GANs and in addition, via an unconditional discriminator, learns the marginal feature distribution of unlabeled images. We empirically show that our model learns highly discriminative CNN features for five datasets, i.e. CUB, SUN, AWA and ImageNet, and establish a new state-of-the-art in any-shot learning, i.e. inductive and transductive (generalized) zero- and few-shot learning settings. We also demonstrate that our learned features are interpretable: we visualize them by inverting them back to the pixel space and we explain them by generating textual arguments of why they are associated with a certain label.

Due to the importance of zero-shot learning, i.e. classifying images where
there is a lack of labeled training data, the number of proposed approaches has
recently increased steadily. We argue that it is time to take a step back and
to analyze the status quo of the area. The purpose of this paper is three-fold.
First, given the fact that there is no agreed upon zero-shot learning
benchmark, we first define a new benchmark by unifying both the evaluation
protocols and data splits of publicly available datasets used for this task.
This is an important contribution as published results are often not comparable
and sometimes even flawed due to, e.g. pre-training on zero-shot test classes.
Moreover, we propose a new zero-shot learning dataset, the Animals with
Attributes 2 (AWA2) dataset which we make publicly available both in terms of
image features and the images themselves. Second, we compare and analyze a
significant number of the state-of-the-art methods in depth, both in the
classic zero-shot setting but also in the more realistic generalized zero-shot
setting. Finally, we discuss in detail the limitations of the current status of
the area which can be taken as a basis for advancing it.

We present a simple yet effective method to infer detailed full human body
shape from only a single photograph. Our model can infer full-body shape
including face, hair, and clothing including wrinkles at interactive
frame-rates. Results feature details even on parts that are occluded in the
input image. Our main idea is to turn shape regression into an aligned
image-to-image translation problem. The input to our method is a partial
texture map of the visible region obtained from off-the-shelf methods. From a
partial texture, we estimate detailed normal and vector displacement maps,
which can be applied to a low-resolution smooth body model to add detail and
clothing. Despite being trained purely with synthetic data, our model
generalizes well to real-world photographs. Numerous results demonstrate the
versatility and robustness of our method.

Internal thought refers to the process of directing attention away from a
primary visual task to internal cognitive processing. Internal thought is a
pervasive mental activity and closely related to primary task performance. As
such, automatic detection of internal thought has significant potential for
user modelling in intelligent interfaces, particularly for e-learning
applications. Despite the close link between the eyes and the human mind, only
a few studies have investigated vergence behaviour during internal thought and
none has studied moment-to-moment detection of internal thought from gaze.
While prior studies relied on long-term data analysis and required a large
number of gaze characteristics, we describe a novel method that is
computationally light-weight and that only requires eye vergence information
that is readily available from binocular eye trackers. We further propose a
novel paradigm to obtain ground truth internal thought annotations that
exploits human blur perception. We evaluate our method for three increasingly
challenging detection tasks: (1) during a controlled math-solving task, (2)
during natural viewing of lecture videos, and (3) during daily activities, such
as coding, browsing, and reading. Results from these evaluations demonstrate
the performance and robustness of vergence-based detection of internal thought
and, as such, open up new directions for research on interfaces that adapt to
shifts of mental attention.

Recent methods to automatically calibrate stationary eye trackers were shown
to effectively reduce inherent calibration distortion. However, these methods
require additional information, such as mouse clicks or on-screen content. We
propose the first method that only requires users' eye movements to reduce
calibration distortion in the background while users naturally look at an
interface. Our method exploits that calibration distortion makes straight
saccade trajectories appear curved between the saccadic start and end points.
We show that this curving effect is systematic and the result of distorted gaze
projection plane. To mitigate calibration distortion, our method undistorts
this plane by straightening saccade trajectories using image warping. We show
that this approach improves over the common six-point calibration and is
promising for reducing distortion. As such, it provides a non-intrusive
solution to alleviating accuracy decrease of eye tracker during long-term use.

We consider general discrete Markov Random Fields(MRFs) with additional
bottleneck potentials which penalize the maximum (instead of the sum) over
local potential value taken by the MRF-assignment. Bottleneck potentials or
analogous constructions have been considered in (i) combinatorial optimization
(e.g. bottleneck shortest path problem, the minimum bottleneck spanning tree
problem, bottleneck function minimization in greedoids), (ii) inverse problems
with $L_{\infty}$-norm regularization, and (iii) valued constraint satisfaction
on the $(\min,\max)$-pre-semirings. Bottleneck potentials for general discrete
MRFs are a natural generalization of the above direction of modeling work to
Maximum-A-Posteriori (MAP) inference in MRFs. To this end, we propose MRFs
whose objective consists of two parts: terms that factorize according to (i)
$(\min,+)$, i.e. potentials as in plain MRFs, and (ii) $(\min,\max)$, i.e.
bottleneck potentials. To solve the ensuing inference problem, we propose
high-quality relaxations and efficient algorithms for solving them. We
empirically show efficacy of our approach on large scale seismic horizon
tracking problems.

Generative Adversarial Networks (GANs) can achieve state-of-the-art sample
quality in generative modelling tasks but suffer from the mode collapse
problem. Variational Autoencoders (VAE) on the other hand explicitly maximize a
reconstruction-based data log-likelihood forcing it to cover all modes, but
suffer from poorer sample quality. Recent works have proposed hybrid VAE-GAN
frameworks which integrate a GAN-based synthetic likelihood to the VAE
objective to address both the mode collapse and sample quality issues, with
limited success. This is because the VAE objective forces a trade-off between
the data log-likelihood and divergence to the latent prior. The synthetic
likelihood ratio term also shows instability during training. We propose a
novel objective with a "Best-of-Many-Samples" reconstruction cost and a stable
direct estimate of the synthetic likelihood. This enables our hybrid VAE-GAN
framework to achieve high data log-likelihood and low divergence to the latent
prior at the same time and shows significant improvement over both hybrid
VAE-GANS and plain GANs in mode coverage and quality.

Meta-learning has been shown to be an effective strategy for few-shot
learning. The key idea is to leverage a large number of similar few-shot tasks
in order to meta-learn how to best initiate a (single) base-learner for novel
few-shot tasks. While meta-learning how to initialize a base-learner has shown
promising results, it is well known that hyperparameter settings such as the
learning rate and the weighting of the regularization term are important to
achieve best performance. We thus propose to also meta-learn these
hyperparameters and in fact learn a time- and layer-varying scheme for learning
a base-learner on novel tasks. Additionally, we propose to learn not only a
single base-learner but an ensemble of several base-learners to obtain more
robust results. While ensembles of learners have shown to improve performance
in various settings, this is challenging for few-shot learning tasks due to the
limited number of training samples. Therefore, our approach also aims to
meta-learn how to effectively combine several base-learners. We conduct
extensive experiments and report top performance for five-class few-shot
recognition tasks on two challenging benchmarks: miniImageNet and
Fewshot-CIFAR100 (FC100).

Understanding physical phenomena is a key competence that enables humans and
animals to act and interact under uncertain perception in previously unseen
environments containing novel objects and their configurations. In this work,
we consider the problem of autonomous block stacking and explore solutions to
learning manipulation under physics constraints with visual perception inherent
to the task. Inspired by the intuitive physics in humans, we first present an
end-to-end learning-based approach to predict stability directly from
appearance, contrasting a more traditional model-based approach with explicit
3D representations and physical simulation. We study the model's behavior
together with an accompanied human subject test. It is then integrated into a
real-world robotic system to guide the placement of a single wood block into
the scene without collapsing existing tower structure. To further automate the
process of consecutive blocks stacking, we present an alternative approach
where the model learns the physics constraint through the interaction with the
environment, bypassing the dedicated physics learning as in the former part of
this work. In particular, we are interested in the type of tasks that require
the agent to reach a given goal state that may be different for every new
trial. Thereby we propose a deep reinforcement learning framework that learns
policies for stacking tasks which are parametrized by a target structure.

Today's deep learning systems deliver high performance based on end-to-end
training. While they deliver strong performance, these systems are hard to
interpret. To address this issue, we propose Semantic Bottleneck Networks
(SBN): deep networks with semantically interpretable intermediate layers that
all downstream results are based on. As a consequence, the analysis on what the
final prediction is based on is transparent to the engineer and failure cases
and modes can be analyzed and avoided by high-level reasoning. We present a
case study on street scene segmentation to demonstrate the feasibility and
power of SBN. In particular, we start from a well performing classic deep
network which we adapt to house a SB-Layer containing task related semantic
concepts (such as object-parts and materials). Importantly, we can recover
state of the art performance despite a drastic dimensionality reduction from
1000s (non-semantic feature) to 10s (semantic concept) channels. Additionally
we show how the activations of the SB-Layer can be used for both the
interpretation of failure cases of the network as well as for confidence
prediction of the resulting output. For the first time, e.g., we show
interpretable segmentation results for most predictions at over 99% accuracy.

Image-to-image (I2I) translation is a pixel-level mapping that requires a
large number of paired training data and often suffers from the problems of
high diversity and strong category bias in image scenes. In order to tackle
these problems, we propose a novel BiLevel (BiL) learning paradigm that
alternates the learning of two models, respectively at an instance-specific
(IS) and a general-purpose (GP) level. In each scene, the IS model learns to
maintain the specific scene attributes. It is initialized by the GP model that
learns from all the scenes to obtain the generalizable translation knowledge.
This GP initialization gives the IS model an efficient starting point, thus
enabling its fast adaptation to the new scene with scarce training data. We
conduct extensive I2I translation experiments on human face and street view
datasets. Quantitative results validate that our approach can significantly
boost the performance of classical I2I translation models, such as PG2 and
Pix2Pix. Our visualization results show both higher image quality and more
appropriate instance-specific details, e.g., the translated image of a person
looks more like that person in terms of identity.

We present a real-time approach for multi-person 3D motion capture at over 30
fps using a single RGB camera. It operates in generic scenes and is robust to
difficult occlusions both by other people and objects. Our method operates in
subsequent stages. The first stage is a convolutional neural network (CNN) that
estimates 2D and 3D pose features along with identity assignments for all
visible joints of all individuals. We contribute a new architecture for this
CNN, called SelecSLS Net, that uses novel selective long and short range skip
connections to improve the information flow allowing for a drastically faster
network without compromising accuracy. In the second stage, a fully-connected
neural network turns the possibly partial (on account of occlusion) 2D pose and
3D pose features for each subject into a complete 3D pose estimate per
individual. The third stage applies space-time skeletal model fitting to the
predicted 2D and 3D pose per subject to further reconcile the 2D and 3D pose,
and enforce temporal coherence. Our method returns the full skeletal pose in
joint angles for each subject. This is a further key distinction from previous
work that neither extracted global body positions nor joint angle results of a
coherent skeleton in real time for multi-person scenes. The proposed system
runs on consumer hardware at a previously unseen speed of more than 30 fps
given 512x320 images as input while achieving state-of-the-art accuracy, which
we will demonstrate on a range of challenging real-world scenes.

Modern approaches to pose and body shape estimation have recently achieved
strong performance even under challenging real-world conditions. Even from a
single image of a clothed person, a realistic looking body shape can be
inferred that captures a users' weight group and body shape type well. This
opens up a whole spectrum of applications -- in particular in fashion -- where
virtual try-on and recommendation systems can make use of these new and
automatized cues. However, a realistic depiction of the undressed body is
regarded highly private and therefore might not be consented by most people.
Hence, we ask if the automatic extraction of such information can be
effectively evaded. While adversarial perturbations have been shown to be
effective for manipulating the output of machine learning models -- in
particular, end-to-end deep learning approaches -- state of the art shape
estimation methods are composed of multiple stages. We perform the first
investigation of different strategies that can be used to effectively
manipulate the automatic shape estimation while preserving the overall
appearance of the original image.

Visual search is an important task, and it is part of daily human life. Thus, it has been a long-standing goal in Computer Vision to develop methods aiming at analysing human search intent and preferences. As the target of the search only exists in mind of the person, search intent prediction remains challenging for machine perception. In this thesis, we focus on advancing techniques for search target and preference prediction from implicit human cues. First, we propose a search target inference algorithm from human fixation data recorded during visual search. In contrast to previous work that has focused on individual instances as a search target in a closed world, we propose the first approach to predict the search target in open-world settings by learning the compatibility between observed fixations and potential search targets. Second, we further broaden the scope of search target prediction to categorical classes, such as object categories and attributes. However, state of the art models for categorical recognition, in general, require large amounts of training data, which is prohibitive for gaze data. To address this challenge, we propose a novel Gaze Pooling Layer that integrates gaze information into CNN-based architectures as an attention mechanism – incorporating both spatial and temporal aspects of human gaze behaviour. Third, we go one step further and investigate the feasibility of combining our gaze embedding approach, with the power of generative image models to visually decode, i.e. create a visual representation of, the search target. Forth, for the first time, we studied the effect of body shape on people preferences of outfits. We propose a novel and robust multi-photo approach to estimate the body shapes of each user and build a conditional model of clothing categories given body-shape. We demonstrate that in real-world data, clothing categories and body-shapes are correlated. We show that our approach estimates a realistic looking body shape that captures a user’s weight group and body shape type, even from a single image of a clothed person. However, an accurate depiction of the naked body is considered highly private and therefore, might not be consented by most people. First, we studied the perception of such technology via a user study. Then, in the last part of this thesis, we ask if the automatic extraction of such information can be effectively evaded. In summary, this thesis addresses several different tasks that aims to enable the vision system to analyse human search intent and preferences in real-world scenarios. In particular, the thesis proposes several novel ideas and models in visual search target prediction from human fixation data, for the first time studied the correlation between shape and clothing categories opening a new direction in clothing recommendation systems, and introduces a new topic in privacy and computer vision, aimed at preventing automatic 3D shape extraction from images.

Eye tracking and gaze-based human-computer interfaces have become a practical modality in desktop settings, since remote eye tracking is efficient and affordable. However, remote eye tracking remains constrained to indoor, laboratory-like conditions, in which lighting and user position need to be controlled. Mobile eye tracking has the potential to overcome these limitations and to allow people to move around freely and to use eye tracking on a daily basis during their everyday routine. However, mobile eye tracking currently faces two fundamental challenges that prevent it from being practically usable and that, consequently, have to be addressed before mobile eye tracking can truly be used by everyone: Mobile eye tracking needs to be advanced and made fully functional in unconstrained environments, and it needs to be made socially acceptable. Numerous sensing and analysis methods were initially developed for remote eye tracking and have been successfully applied for decades. Unfortunately, these methods are limited in terms of functionality and correctness, or even unsuitable for application in mobile eye tracking. Therefore, the majority of fundamental definitions, eye tracking methods, and gaze estimation approaches cannot be borrowed from remote eye tracking without adaptation. For example, the definitions of specific eye movements, like classical fixations, need to be extended to mobile settings where natural user and head motion are omnipresent. Corresponding analytical methods need to be adjusted or completely reimplemented based on novel approaches encoding the human gaze behaviour. Apart from these technical challenges, an entirely new, and yet under-explored, topic required for the breakthrough of mobile eye tracking as everyday technology is the overcoming of social obstacles. A first crucial key issue to defuse social objections is the building of acceptance towards mobile eye tracking. Hence, it is essential to replace the bulky appearance of current head-mounted eye trackers with an unobtrusive, appealing, and trendy design. The second high-priority theme of increasing importance for everyone is privacy and its protection, given that research and industry have not focused on or taken care of this problem at all. To establish true confidence, future devices have to find a fine balance between protecting users’ and bystanders’ privacy and attracting and convincing users of their necessity, utility, and potential with useful and beneficial features. The solution of technical challenges and social obstacles is the prerequisite for the development of a variety of novel and exciting applications in order to establish mobile eye tracking as a new paradigm, which ease our everyday life. This thesis addresses core technical challenges of mobile eye tracking that currently prevent it from being widely adopted. Specifically, this thesis proves that 3D data used for the calibration of mobile eye trackers improves gaze estimation and significantly reduces the parallax error. Further, it presents the first effective fixation detection method for head-mounted devices that is robust against the prevalence of user and gaze target motion. In order to achieve social acceptability, this thesis proposes an innovative and unobtrusive design for future mobile eye tracking devices and builds the first prototype with fully frame-embedded eye cameras combined with a calibration-free deep-trained appearance-based gaze estimation approach. To protect users’ and bystanders’ privacy in the presence of head-mounted eye trackers, this thesis presents another first-of-its-kind prototype. It is able to identify privacy-sensitive situations to automatically enable and disable the eye tracker’s first-person camera by means of a mechanical shutter, leveraging the combination of deep scene and eye movement features. Nevertheless, solving technical challenges and social obstacles alone is not sufficient to make mobile eye tracking attractive for the masses. The key to success is the development of convincingly useful, innovative, and essential applications. To extend the protection of users’ privacy on the software side as well, this thesis presents the first privacy-aware VR gaze interface using differential privacy. This method adds noise to recorded eye tracking data so that privacy-sensitive information like a user’s gender or identity is protected without impeding the utility of the data itself. In addition, the first large-scale online survey is conducted to understand users’ concerns with eye tracking. To develop and evaluate novel applications, this thesis presents the first publicly available long-term eye tracking datasets. They are used to show the unsupervised detection of users’ activities from eye movements alone using novel and efficient video-based encoding approaches as well as to propose the first proof-of-concept method to forecast users’ attentive behaviour during everyday mobile interactions from phone-integrated and body-worn sensors. This opens up possibilities for the development of a variety of novel and exciting applications. With more advanced features, accompanied by technological progress and sensor miniaturisation, eye tracking is increasingly integrated into conventional glasses as well as virtual and augmented reality (VR/AR) head-mounted displays, becoming an integral component of mobile interfaces. This thesis paves the way for the development of socially acceptable, privacy-aware, but highly functional mobile eye tracking devices and novel applications, so that mobile eye tracking can develop its full potential to become an everyday technology for everyone.

Adversarial training is the standard to train models robust against
adversarial examples. However, especially for complex datasets, adversarial
training incurs a significant loss in accuracy and is known to generalize
poorly to stronger attacks, e.g., larger perturbations or other threat models.
In this paper, we introduce confidence-calibrated adversarial training (CCAT)
where the key idea is to enforce that the confidence on adversarial examples
decays with their distance to the attacked examples. We show that CCAT
preserves better the accuracy of normal training while robustness against
adversarial examples is achieved via confidence thresholding, i.e., detecting
adversarial examples based on their confidence. Most importantly, in strong
contrast to adversarial training, the robustness of CCAT generalizes to larger
perturbations and other threat models, not encountered during training. For
evaluation, we extend the commonly used robust test error to our detection
setting, present an adaptive attack with backtracking and allow the attacker to
select, per test example, the worst-case adversarial example from multiple
black- and white-box attacks. We present experimental results using $L_\infty$,
$L_2$, $L_1$ and $L_0$ attacks on MNIST, SVHN and Cifar10.

While great progress has been made recently in automatic image manipulation,
it has been limited to object centric images like faces or structured scene
datasets. In this work, we take a step towards general scene-level image
editing by developing an automatic interaction-free object removal model. Our
model learns to find and remove objects from general scene images using
image-level labels and unpaired data in a generative adversarial network (GAN)
framework. We achieve this with two key contributions: a two-stage editor
architecture consisting of a mask generator and image in-painter that
co-operate to remove objects, and a novel GAN based prior for the mask
generator that allows us to flexibly incorporate knowledge about object shapes.
We experimentally show on two datasets that our method effectively removes a
wide variety of objects using weak supervision only

Deep neural perception and control networks have become key com-
ponents of self-driving vehicles. User acceptance is likely to benefit from easy-
to-interpret textual explanations which allow end-users to understand what trig-
gered a particular behavior. Explanations may be triggered by the neural con-
troller, namely
introspective explanations
, or informed by the neural controller’s
output, namely
rationalizations
. We propose a new approach to introspective ex-
planations which consists of two parts. First, we use a visual (spatial) attention
model to train a convolutional network end-to-end from images to the vehicle
control commands,
i
.
e
., acceleration and change of course. The controller’s at-
tention identifies image regions that potentially influence the network’s output.
Second, we use an attention-based video-to-text model to produce textual ex-
planations of model actions. The attention maps of controller and explanation
model are aligned so that explanations are grounded in the parts of the scene that
mattered to the controller. We explore two approaches to attention alignment,
strong- and weak-alignment. Finally, we explore a version of our model that
generates rationalizations, and compare with introspective explanations on the
same video segments. We evaluate these models on a novel driving dataset with
ground-truth human explanations, the Berkeley DeepDrive eXplanation (BDD-
X) dataset. Code is available at
github.com/JinkyuKimUCB/explainable-deep-driving

Encouraged by the recent progress in pedestrian detection, we investigate the gap between current state-of-the-art methods

and the “perfect single frame detector”. We enable our analysis by creating a human baseline for pedestrian detection (over the Caltech

pedestrian dataset). After manually clustering the frequent errors of a top detector, we characterise both localisation and background-

versus-foreground errors.

To address localisation errors we study the impact of training annotation noise on the detector performance, and show that we can

improve results even with a small portion of sanitised training data. To address background/foreground discrimination, we study convnets

for pedestrian detection, and discuss which factors affect their performance.

Other than our in-depth analysis, we report top performance on the Caltech pedestrian dataset, and provide a new sanitised set of

training and test annotations.

Natural language explanations of deep neural network decisions provide an
intuitive way for a AI agent to articulate a reasoning process. Current textual
explanations learn to discuss class discriminative features in an image.
However, it is also helpful to understand which attributes might change a
classification decision if present in an image (e.g., "This is not a Scarlet
Tanager because it does not have black wings.") We call such textual
explanations counterfactual explanations, and propose an intuitive method to
generate counterfactual explanations by inspecting which evidence in an input
is missing, but might contribute to a different classification decision if
present in the image. To demonstrate our method we consider a fine-grained
image classification task in which we take as input an image and a
counterfactual class and output text which explains why the image does not
belong to a counterfactual class. We then analyze our generated counterfactual
explanations both qualitatively and quantitatively using proposed automatic
metrics.

The inner structure of a material is called microstructure. It stores the

genesis of a material and determines all its physical and chemical properties.

While microstructural characterization is widely spread and well known, the

microstructural classification is mostly done manually by human experts, which

opens doors for huge uncertainties. Since the microstructure could be a

combination of different phases with complex substructures its automatic

classification is very challenging and just a little work in this field has

been carried out. Prior related works apply mostly designed and engineered

features by experts and classify microstructure separately from feature

extraction step. Recently Deep Learning methods have shown surprisingly good

performance in vision applications by learning the features from data together

with the classification step. In this work, we propose a deep learning method

for microstructure classification in the examples of certain microstructural

constituents of low carbon steel. This novel method employs pixel-wise

segmentation via Fully Convolutional Neural Networks (FCNN) accompanied by

max-voting scheme. Our system achieves 93.94% classification accuracy,

drastically outperforming the state-of-the-art method of 48.89% accuracy,

indicating the effectiveness of pixel-wise approaches. Beyond the success

presented in this paper, this line of research offers a more robust and first

of all objective way for the difficult task of steel quality appreciation.

The matching of multiple objects (e.g. shapes or images) is a fundamental
problem in vision and graphics. In order to robustly handle ambiguities, noise
and repetitive patterns in challenging real-world settings, it is essential to
take geometric consistency between points into account. Computationally, the
multi-matching problem is difficult. It can be phrased as simultaneously
solving multiple (NP-hard) quadratic assignment problems (QAPs) that are
coupled via cycle-consistency constraints. The main limitations of existing
multi-matching methods are that they either ignore geometric consistency and
thus have limited robustness, or they are restricted to small-scale problems
due to their (relatively) high computational cost. We address these
shortcomings by introducing a Higher-order Projected Power Iteration method,
which is (i) efficient and scales to tens of thousands of points, (ii)
straightforward to implement, (iii) able to incorporate geometric consistency,
and (iv) guarantees cycle-consistent multi-matchings. Experimentally we show
that our approach is superior to existing methods.

For autonomous agents to successfully operate in the real world, anticipation

of future events and states of their environment is a key competence. This

problem can be formalized as a sequence prediction problem, where a number of

observations are used to predict the sequence into the future. However,

real-world scenarios demand a model of uncertainty of such predictions, as

future states become increasingly uncertain and multi-modal -- in particular on

long time horizons. This makes modelling and learning challenging. We cast

state of the art semantic segmentation and future prediction models based on

deep learning into a Bayesian formulation that in turn allows for a full

Bayesian treatment of the prediction problem. We present a new sampling scheme

for this model that draws from the success of variational autoencoders by

incorporating a recognition network. In the experiments we show that our model

outperforms prior work in accuracy of the predicted segmentation and provides

calibrated probabilities that also better capture the multi-modal aspects of

possible future states of street scenes.

We introduce Primal-Dual Wasserstein GAN, a new learning algorithm for

building latent variable models of the data distribution based on the primal

and the dual formulations of the optimal transport (OT) problem. We utilize the

primal formulation to learn a flexible inference mechanism and to create an

optimal approximate coupling between the data distribution and the generative

model. In order to learn the generative model, we use the dual formulation and

train the decoder adversarially through a critic network that is regularized by

the approximate coupling obtained from the primal. Unlike previous methods that

violate various properties of the optimal critic, we regularize the norm and

the direction of the gradients of the critic function. Our model shares many of

the desirable properties of auto-encoding models in terms of mode coverage and

latent structure, while avoiding their undesirable averaging properties, e.g.

their inability to capture sharp visual features when modeling real images. We

compare our algorithm with several other generative modeling techniques that

utilize Wasserstein distances on Frechet Inception Distance (FID) and Inception

Scores (IS).

With the widespread use of machine learning (ML) techniques, ML as a service
has become increasingly popular. In this setting, an ML model resides on a
server and users can query the model with their data via an API. However, if
the user's input is sensitive, sending it to the server is not an option.
Equally, the service provider does not want to share the model by sending it to
the client for protecting its intellectual property and pay-per-query business
model. In this paper, we propose MLCapsule, a guarded offline deployment of
machine learning as a service. MLCapsule executes the machine learning model
locally on the user's client and therefore the data never leaves the client.
Meanwhile, MLCapsule offers the service provider the same level of control and
security of its model as the commonly used server-side execution. In addition,
MLCapsule is applicable to offline applications that require local execution.
Beyond protecting against direct model access, we demonstrate that MLCapsule
allows for implementing defenses against advanced attacks on machine learning
models such as model stealing/reverse engineering and membership inference.

In this study, we explore building a two-stage framework for enabling users

to directly manipulate high-level attributes of a natural scene. The key to our

approach is a deep generative network which can hallucinate images of a scene

as if they were taken at a different season (e.g. during winter), weather

condition (e.g. in a cloudy day) or time of the day (e.g. at sunset). Once the

scene is hallucinated with the given attributes, the corresponding look is then

transferred to the input image while preserving the semantic details intact,

giving a photo-realistic manipulation result. As the proposed framework

hallucinates what the scene will look like, it does not require any reference

style image as commonly utilized in most of the appearance or style transfer

approaches. Moreover, it allows to simultaneously manipulate a given scene

according to a diverse set of transient attributes within a single model,

eliminating the need of training multiple networks per each translation task.

Our comprehensive set of qualitative and quantitative results demonstrate the

effectiveness of our approach against the competing methods.

We propose a novel approach to jointly perform 3D object retrieval and pose
estimation from monocular images.In order to make the method robust to real
world scene variations in the images, e.g. texture, lighting and background,we
learn an embedding space from 3D data that only includes the relevant
information, namely the shape and pose.Our method can then be trained for
robustness under real world scene variations without having to render a large
training set simulating these variations. Our learned embedding explicitly
disentangles a shape vector and a pose vector, which alleviates both pose bias
for 3D shape retrieval and categorical bias for pose estimation. Having the
learned disentangled embedding, we train a CNN to map the images to the
embedding space, and then retrieve the closest 3D shape from the database and
estimate the 6D pose of the object using the embedding vectors. Our method
achieves 10.8 median error for pose estimation and 0.514 top-1-accuracy for
category agnostic 3D object retrieval on the Pascal3D+ dataset. It therefore
outperforms the previous state-of-the-art methods on both tasks.

From autonomous driving cars to surgical robots, robotic system has enjoyed significant growth over the past decade. With the rapid development in robotics alongside the evolution in the related fields, such as computer vision and machine learning, integrating perception, anticipation and manipulation is key to the success of future robotic system. In this thesis, we explore different ways of such integration to extend the capabilities of a robotic system to take on more challenging real world tasks. On anticipation and perception, we address the recognition of ongoing activity from videos. In particular we focus on long-duration and complex activities and hence propose a new challenging dataset to facilitate the work. We introduce hierarchical labels over the activity classes and investigate the temporal accuracy-specificity trade-offs. We propose a new method based on recurrent neural networks that learns to predict over this hierarchy and realize accuracy specificity trade-offs. Our method outperforms several baselines on this new challenge. On manipulation with perception, we propose an efficient framework for programming a robot to use human tools. We first present a novel and compact model for using tools described by a tip model. Then we explore a strategy of utilizing a dual-gripper approach for manipulating tools – motivated by the absence of dexterous hands on widely available general purpose robots. Afterwards, we embed the tool use learning into a hierarchical architecture and evaluate it on a Baxter research robot. Finally, combining perception, anticipation and manipulation, we focus on a block stacking task. First we explore how to guide robot to place a single block into the scene without collapsing the existing structure. We introduce a mechanism to predict physical stability directly from visual input and evaluate it first on a synthetic data and then on real-world block stacking. Further, we introduce the target stacking task where the agent stacks blocks to reproduce a tower shown in an image. To do so, we create a synthetic block stacking environment with physics simulation in which the agent can learn block stacking end-to-end through trial and error, bypassing to explicitly model the corresponding physics knowledge. We propose a goal-parametrized GDQN model to plan with respect to the specific goal. We validate the model on both a navigation task in a classic gridworld environment and the block stacking task.

We propose a deep representation of appearance, i. e. the relation of color,

surface orientation, viewer position, material and illumination. Previous

approaches have used deep learning to extract classic appearance

representations relating to reflectance model parameters (e. g. Phong) or

illumination (e. g. HDR environment maps). We suggest to directly represent

appearance itself as a network we call a deep appearance map (DAM). This is a

4D generalization over 2D reflectance maps, which held the view direction

fixed. First, we show how a DAM can be learned from images or video frames and

later be used to synthesize appearance, given new surface orientations and

viewer positions. Second, we demonstrate how another network can be used to map

from an image or video frames to a DAM network to reproduce this appearance,

without using a lengthy optimization such as stochastic gradient descent

(learning-to-learn). Finally, we generalize this to an appearance

estimation-and-segmentation task, where we map from an image showing multiple

materials to multiple networks reproducing their appearance, as well as

per-pixel segmentation.

Machine learning is transforming the world. Its application areas span privacy
sensitive and security critical tasks such as human identification and self-driving
cars. These applications raise privacy and security related questions that are not
fully understood or answered yet: Can automatic person recognisers identify people
in photos even when their faces are blurred? How easy is it to find an adversarial
input for a self-driving car that makes it drive off the road?
This thesis contributes one of the first steps towards a better understanding of
such concerns. We observe that many privacy and security critical scenarios for
learned models involve input data manipulation: users obfuscate their identity by
blurring their faces and adversaries inject imperceptible perturbations to the input
signal. We introduce a data manipulator framework as a tool for collectively describing
and analysing privacy and security relevant scenarios involving learned models.
A data manipulator introduces a shift in data distribution for achieving privacy or
security related goals, and feeds the transformed input to the target model. This
framework provides a common perspective on the studies presented in the thesis.
We begin the studies from the user’s privacy point of view. We analyse the
efficacy of common obfuscation methods like face blurring, and show that they
are surprisingly ineffective against state of the art person recognition systems. We
then propose alternatives based on head inpainting and adversarial examples. By
studying the user privacy, we also study the dual problem: model security. In model
security perspective, a model ought to be robust and reliable against small amounts
of data manipulation. In both cases, data are manipulated with the goal of changing
the target model prediction. User privacy and model security problems can be
described with the same objective.
We then study the knowledge aspect of the data manipulation problem. The more
one knows about the target model, the more effective manipulations one can craft.
We propose a game theoretic manipulation framework to systematically represent
the knowledge level on the target model and derive privacy and security guarantees.
We then discuss ways to increase knowledge about a black-box model by only querying
it, deriving implications that are relevant to both privacy and security perspectives.

Machine Learning techniques are widely used by online services (e.g. Google,

Apple) in order to analyze and make predictions on user data. As many of the

provided services are user-centric (e.g. personal photo collections, speech

recognition, personal assistance), user data generated on personal devices is

key to provide the service. In order to protect the data and the privacy of the

user, federated learning techniques have been proposed where the data never

leaves the user's device and "only" model updates are communicated back to the

server. In our work, we propose a new threat model that is not concerned with

learning about the content - but rather is concerned with the linkability of

users during such decentralized learning scenarios.

We show that model updates are characteristic for users and therefore lend

themselves to linkability attacks. We show identification and matching of users

across devices in closed and open world scenarios. In our experiments, we find

our attacks to be highly effective, achieving 20x-175x chance-level

performance.

In order to mitigate the risks of linkability attacks, we study various

strategies. As adding random noise does not offer convincing operation points,

we propose strategies based on using calibrated domain-specific data; we find

these strategies offers substantial protection against linkability threats with

little effect to utility.

We propose a novel end-to-end trainable framework for the graph decomposition
problem. The minimum cost multicut problem is first converted to an
unconstrained binary cubic formulation where cycle consistency constraints are
incorporated into the objective function. The new optimization problem can be
viewed as a Conditional Random Field (CRF) in which the random variables are
associated with the binary edge labels of the initial graph and the hard
constraints are introduced in the CRF as high-order potentials. The parameters
of a standard Neural Network and the fully differentiable CRF are optimized in
an end-to-end manner. Furthermore, our method utilizes the cycle constraints as
meta-supervisory signals during the learning of the deep feature
representations by taking the dependencies between the output random variables
into account. We present analyses of the end-to-end learned representations,
showing the impact of the joint training, on the task of clustering images of
MNIST. We also validate the effectiveness of our approach both for the feature
learning and the final clustering on the challenging task of real-world
multi-person pose estimation.

As first-person cameras in head-mounted displays become increasingly

prevalent, so does the problem of infringing user and bystander privacy. To

address this challenge, we present PrivacEye, a proof-of-concept system that

detects privacysensitive everyday situations and automatically enables and

disables the first-person camera using a mechanical shutter. To close the

shutter, PrivacEye detects sensitive situations from first-person camera videos

using an end-to-end deep-learning model. To open the shutter without visual

input, PrivacEye uses a separate, smaller eye camera to detect changes in

users' eye movements to gauge changes in the "privacy level" of the current

situation. We evaluate PrivacEye on a dataset of first-person videos recorded

in the daily life of 17 participants that they annotated with privacy

sensitivity levels. We discuss the strengths and weaknesses of our

proof-of-concept system based on a quantitative technical evaluation as well as

qualitative insights from semi-structured interviews.

Following a period of expedited progress in the capabilities of digital systems, the society begins to realize that systems designed to assist people in various tasks can also harm individuals and society. Mediating access to information and explicitly or implicitly ranking people in increasingly many applications, search systems have a substantial potential to contribute to such unwanted outcomes. Since they collect vast amounts of data about both searchers and search subjects, they have the potential to violate the privacy of both of these groups of users. Moreover, in applications where rankings influence people's economic livelihood outside of the platform, such as sharing economy or hiring support websites, search engines have an immense economic power over their users in that they control user exposure in ranked results. This thesis develops new models and methods broadly covering different aspects of privacy and fairness in search systems for both searchers and search subjects. Specifically, it makes the following contributions: (1) We propose a model for computing individually fair rankings where search subjects get exposure proportional to their relevance. The exposure is amortized over time using constrained optimization to overcome searcher attention biases while preserving ranking utility. (2) We propose a model for computing sensitive search exposure where each subject gets to know the sensitive queries that lead to her profile in the top-k search results. The problem of finding exposing queries is technically modeled as reverse nearest neighbor search, followed by a weekly-supervised learning to rank model ordering the queries by privacy-sensitivity. (3) We propose a model for quantifying privacy risks from textual data in online communities. The method builds on a topic model where each topic is annotated by a crowdsourced sensitivity score, and privacy risks are associated with a user's relevance to sensitive topics. We propose relevance measures capturing different dimensions of user interest in a topic and show how they correlate with human risk perceptions. (4) We propose a model for privacy-preserving personalized search where search queries of different users are split and merged into synthetic profiles. The model mediates the privacy-utility trade-off by keeping semantically coherent fragments of search histories within individual profiles, while trying to minimize the similarity of any of the synthetic profiles to the original user profiles. The models are evaluated using information retrieval techniques and user studies over a variety of datasets, ranging from query logs, through social media and community question answering postings, to item listings from sharing economy platforms.

Convnets have enabled significant progress in pedestrian detection recently,

but there are still open questions regarding suitable architectures and

training data. We revisit CNN design and point out key adaptations, enabling

plain FasterRCNN to obtain state-of-the-art results on the Caltech dataset.

To achieve further improvement from more and better data, we introduce

CityPersons, a new set of person annotations on top of the Cityscapes dataset.

The diversity of CityPersons allows us for the first time to train one single

CNN model that generalizes well over multiple benchmarks. Moreover, with

additional training with CityPersons, we obtain top results using FasterRCNN on

Caltech, improving especially for more difficult cases (heavy occlusion and

small scale) and providing higher localization quality.

Previous work focused on predicting visual search targets from human

fixations but, in the real world, a specific target is often not known, e.g.

when searching for a present for a friend. In this work we instead study the

problem of predicting the mental picture, i.e. only an abstract idea instead of

a specific target. This task is significantly more challenging given that

mental pictures of the same target category can vary widely depending on

personal biases, and given that characteristic target attributes can often not

be verbalised explicitly. We instead propose to use gaze information as

implicit information on users' mental picture and present a novel gaze pooling

layer to seamlessly integrate semantic and localized fixation information into

a deep image representation. We show that we can robustly predict both the

mental picture's category as well as attributes on a novel dataset containing

fixation data of 14 users searching for targets on a subset of the DeepFahion

dataset. Our results have important implications for future search interfaces

and suggest deep gaze pooling as a general-purpose approach for gaze-supported

computer vision systems.

Audio Description (AD) provides linguistic descriptions of movies and allows

visually impaired people to follow a movie along with their peers. Such

descriptions are by design mainly visual and thus naturally form an interesting

data source for computer vision and computational linguistics. In this work we

propose a novel dataset which contains transcribed ADs, which are temporally

aligned to full length movies. In addition we also collected and aligned movie

scripts used in prior work and compare the two sources of descriptions. In

total the Large Scale Movie Description Challenge (LSMDC) contains a parallel

corpus of 118,114 sentences and video clips from 202 movies. First we

characterize the dataset by benchmarking different approaches for generating

video descriptions. Comparing ADs to scripts, we find that ADs are indeed more

visual and describe precisely what is shown rather than what should happen

according to the scripts created prior to movie production. Furthermore, we

present and compare the results of several teams who participated in a

challenge organized in the context of the workshop "Describing and

Understanding Video & The Large Scale Movie Description Challenge (LSMDC)", at

ICCV 2015.

Visual object detection has seen substantial improvements during the last years due to the possibilities enabled by deep learning. While research on image classification provides continuous progress on how to learn image representations and classifiers jointly, object detection research focuses on identifying how to properly use deep learning technology to effectively localise objects. In this thesis, we analyse and improve different aspects of the commonly used detection pipeline. We analyse ten years of research on pedestrian detection and find that improvement of feature representations was the driving factor. Motivated by this finding, we adapt an end-to-end learned detector architecture from general object detection to pedestrian detection. Our deep network outperforms all previous neural networks for pedestrian detection by a large margin, even without using additional training data. After substantial improvements on pedestrian detection in recent years, we investigate the gap between human performance and state-of-the-art pedestrian detectors. We find that pedestrian detectors still have a long way to go before they reach human performance, and we diagnose failure modes of several top performing detectors, giving direction to future research. As a side-effect we publish new, better localised annotations for the Caltech pedestrian benchmark. We analyse detection proposals as a preprocessing step for object detectors. We establish different metrics and compare a wide range of methods according to these metrics. By examining the relationship between localisation of proposals and final object detection performance, we define and experimentally verify a metric that can be used as a proxy for detector performance. Furthermore, we address a structural weakness of virtually all object detection pipelines: non-maximum suppression. We analyse why it is necessary and what the shortcomings of the most common approach are. To address these problems, we present work to overcome these shortcomings and to replace typical non-maximum suppression with a learnable alternative. The introduced paradigm paves the way to true end-to-end learning of object detectors without any post-processing. In summary, this thesis provides analyses of recent pedestrian detectors and detection proposals, improves pedestrian detection by employing deep neural networks, and presents a viable alternative to traditional non-maximum suppression.

Much progress has been made in image and video segmentation
over the last years. To a large extent, the success can be attributed to
the strong appearance models completely learned from data, in particular
using deep learning methods. However,to perform best these methods require
large representative datasets for training with expensive pixel-level
annotations, which in case of videos are prohibitive to obtain. Therefore,
there is a need to relax this constraint and to consider alternative forms
of supervision, which are easier and cheaper to collect. In this thesis,
we aim to develop algorithms for learning to segment in images and videos
with different levels of supervision.
First, we develop approaches for training convolutional networks with weaker
forms of supervision, such as bounding boxes or image labels, for object
boundary estimation and semantic/instance labelling tasks. We propose to
generate pixel-level approximate groundtruth from these weaker forms of
annotations to train a network, which allows to achieve high-quality
results comparable to the full supervision quality without any
modifications of the network architecture or the training procedure.
Second, we address the problem of the excessive computational and memory
costs inherent to solving video segmentation via graphs. We propose
approaches to improve the runtime and memory efficiency as well as the
output segmentation quality by learning from the available training data
the best representation of the graph. In particular, we contribute with
learning must-link constraints, the topology and edge weights of the graph
as well as enhancing the graph nodes - superpixels - themselves.
Third, we tackle the task of pixel-level object tracking and address the
problem of the limited amount of densely annotated video data for training
convolutional networks. We introduce an architecture which allows training
with static images only and propose an elaborate data synthesis scheme
which creates a large number of training examples close to the target
domain from the given first frame mask. With the proposed techniques we
show that densely annotated consequent video data is not necessary to
achieve high-quality temporally coherent video segmentationresults.
In summary, this thesis advances the state of the art in weakly supervised
image segmentation, graph-based video segmentation and pixel-level object
tracking and contributes with the new ways of training convolutional
networks with a limited amount of pixel-level annotated training data.

Convolutional networks reach top quality in pixel-level object tracking but

require a large amount of training data (1k ~ 10k) to deliver such results. We

propose a new training strategy which achieves state-of-the-art results across

three evaluation datasets while using 20x ~ 100x less annotated data than

competing methods. Instead of using large training sets hoping to generalize

across domains, we generate in-domain training data using the provided

annotation on the first frame of each video to synthesize ("lucid dream")

plausible future video frames. In-domain per-video training data allows us to

train high quality appearance- and motion-based models, as well as tune the

post-processing stage. This approach allows to reach competitive results even

when training from only a single annotated frame, without ImageNet

pre-training. Our results indicate that using a larger training set is not

automatically better, and that for the tracking task a smaller training set

that is closer to the target domain is more effective. This changes the mindset

regarding how many training samples and general "objectness" knowledge are

required for the object tracking task.

Modern image classification methods are based on supervised learning algorithms that require labeled training data. However, only a limited amount of annotated data may be available in certain applications due to scarcity of the data itself or high costs associated with human annotation. Introduction of additional information and structural constraints can help improve the performance of a learning algorithm. In this thesis, we study the framework of learning using privileged information and demonstrate its relation to learning with instance weights. We also consider multitask feature learning and develop an efficient dual optimization scheme that is particularly well suited to problems with high dimensional image descriptors. Scaling annotation to a large number of image categories leads to the problem of class ambiguity where clear distinction between the classes is no longer possible. Many real world images are naturally multilabel yet the existing annotation might only contain a single label. In this thesis, we propose and analyze a number of loss functions that allow for a certain tolerance in top k predictions of a learner. Our results indicate consistent improvements over the standard loss functions that put more penalty on the first incorrect prediction compared to the proposed losses. All proposed learning methods are complemented with efficient optimization schemes that are based on stochastic dual coordinate ascent for convex problems and on gradient descent for nonconvex formulations.

Understanding physical phenomena is a key component of human intelligence and

enables physical interaction with previously unseen environments. In this

paper, we study how an artificial agent can autonomously acquire this intuition

through interaction with the environment. We created a synthetic block stacking

environment with physics simulation in which the agent can learn a policy

end-to-end through trial and error. Thereby, we bypass to explicitly model

physical knowledge within the policy. We are specifically interested in tasks

that require the agent to reach a given goal state that may be different for

every new trial. To this end, we propose a deep reinforcement learning

framework that learns policies which are parametrized by a goal. We validated

the model on a toy example navigating in a grid world with different target

positions and in a block stacking task with different target structures of the

final tower. In contrast to prior work, our policies show better generalization

across different goals.

Computer Vision has undergone major changes over the recent five years. Here, we investigate if the performance of such architectures generalizes to more complex tasks that require a more holistic approach to scene comprehension. The presented work focuses on learning spatial and multi-modal representations, and the foundations of a Visual Turing Test, where the scene understanding is tested by a series of questions about its content. In our studies, we propose DAQUAR, the first ‘question answering about real-world images’ dataset together with methods, termed a symbolic-based and a neural-based visual question answering architectures, that address the problem. The symbolic-based method relies on a semantic parser, a database of visual facts, and a bayesian formulation that accounts for various interpretations of the visual scene. The neural-based method is an end-to-end architecture composed of a question encoder, image encoder, multimodal embedding, and answer decoder. This architecture has proven to be effective in capturing language-based biases. It also becomes the standard component of other visual question answering architectures. Along with the methods, we also investigate various evaluation metrics that embraces uncertainty in word's meaning, and various interpretations of the scene and the question.

People nowadays share large parts of their personal lives through social

media. Being able to automatically recognise people in personal photos may

greatly enhance user convenience by easing photo album organisation. For human

identification task, however, traditional focus of computer vision has been

face recognition and pedestrian re-identification. Person recognition in social

media photos sets new challenges for computer vision, including non-cooperative

subjects (e.g. backward viewpoints, unusual poses) and great changes in

appearance. To tackle this problem, we build a simple person recognition

framework that leverages convnet features from multiple image regions (head,

body, etc.). We propose new recognition scenarios that focus on the time and

appearance gap between training and testing samples. We present an in-depth

analysis of the importance of different features according to time and

viewpoint generalisability. In the process, we verify that our simple approach

achieves the state of the art result on the PIPA benchmark, arguably the

largest social media based benchmark for person recognition to date with

diverse poses, viewpoints, social groups, and events.

Compared the conference version of the paper, this paper additionally

presents (1) analysis of a face recogniser (DeepID2+), (2) new method naeil2

that combines the conference version method naeil and DeepID2+ to achieve state

of the art results even compared to post-conference works, (3) discussion of

related work since the conference version, (4) additional analysis including

the head viewpoint-wise breakdown of performance, and (5) results on the

open-world setup.

Many deployed learned models are black boxes: given input, returns output.

Internal information about the model, such as the architecture, optimisation

procedure, or training data, is not disclosed explicitly as it might contain

proprietary information or make the system more vulnerable. This work shows

that such attributes of neural networks can be exposed from a sequence of

queries. This has multiple implications. On the one hand, our work exposes the

vulnerability of black-box neural networks to different types of attacks -- we

show that the revealed internal information helps generate more effective

adversarial examples against the black box model. On the other hand, this

technique can be used for better protection of private content from automatic

recognition models using adversarial examples. Our paper suggests that it is

actually hard to draw a line between white box and black box models.

Deep models are the defacto standard in visual decision problems due to their
impressive performance on a wide array of visual tasks. On the other hand,
their opaqueness has led to a surge of interest in explainable systems. In this
work, we emphasize the importance of model explanation in various forms such as
visual pointing and textual justification. The lack of data with justification
annotations is one of the bottlenecks of generating multimodal explanations.
Thus, we propose two large-scale datasets with annotations that visually and
textually justify a classification decision for various activities, i.e. ACT-X,
and for question answering, i.e. VQA-X. We also introduce a multimodal
methodology for generating visual and textual explanations simultaneously. We
quantitatively show that training with the textual explanations not only yields
better textual justification models, but also models that better localize the
evidence that support their decision.

Generating natural language descriptions for visual data links computer vision and computational linguistics. Being able to generate a concise and human-readable description of a video is a step towards visual understanding. At the same time, grounding natural language in visual data provides disambiguation for the linguistic concepts, necessary for many applications. This thesis focuses on both directions and tackles three specific problems. First, we develop recognition approaches to understand video of complex cooking activities. We propose an approach to generate coherent multi-sentence descriptions for our videos. Furthermore, we tackle the new task of describing videos at variable level of detail. Second, we present a large-scale dataset of movies and aligned professional descriptions. We propose an approach, which learns from videos and sentences to describe movie clips relying on robust recognition of visual semantic concepts. Third, we propose an approach to ground textual phrases in images with little or no localization supervision, which we further improve by introducing Multimodal Compact Bilinear Pooling for combining language and vision representations. Finally, we jointly address the task of describing videos and grounding the described people. To summarize, this thesis advances the state-of-the-art in automatic video description and visual grounding and also contributes large datasets for studying the intersection of computer vision and computational linguistics.

What does human gaze reveal about a users' intents and to which extend can

these intents be inferred or even visualized? Gaze was proposed as an implicit

source of information to predict the target of visual search and, more

recently, to predict the object class and attributes of the search target. In

this work, we go one step further and investigate the feasibility of combining

recent advances in encoding human gaze information using deep convolutional

neural networks with the power of generative image models to visually decode,

i.e. create a visual representation of, the search target. Such visual decoding

is challenging for two reasons: 1) the search target only resides in the user's

mind as a subjective visual pattern, and can most often not even be described

verbally by the person, and 2) it is, as of yet, unclear if gaze fixations

contain sufficient information for this task at all. We show, for the first

time, that visual representations of search targets can indeed be decoded only

from human gaze fixations. We propose to first encode fixations into a semantic

representation and then decode this representation into an image. We evaluate

our method on a recent gaze dataset of 14 participants searching for clothing

in image collages and validate the model's predictions using two human studies.

Our results show that 62% (Chance level = 10%) of the time users were able to

select the categories of the decoded image right. In our second studies we show

the importance of a local gaze encoding for decoding visual search targets of

user

People are often a central element of visual scenes, particularly in real-world street scenes. Thus it has been a long-standing goal in Computer Vision to develop methods aiming at analyzing humans in visual data. Due to the complexity of real-world scenes, visual understanding of people remains challenging for machine perception. In this thesis we focus on advancing the techniques for people detection and tracking in crowded street scenes. We also propose new models for human pose estimation and motion segmentation in realistic images and videos. First, we propose detection models that are jointly trained to detect single person as well as pairs of people under varying degrees of occlusion. The learning algorithm of our joint detector facilitates a tight integration of tracking and detection, because it is designed to address common failure cases during tracking due to long-term inter-object occlusions. Second, we propose novel multi person tracking models that formulate tracking as a graph partitioning problem. Our models jointly cluster detection hypotheses in space and time, eliminating the need for a heuristic non-maximum suppression. Furthermore, for crowded scenes, our tracking model encodes long-range person re-identification information into the detection clustering process in a unified and rigorous manner. Third, we explore the visual tracking task in different granularity. We present a tracking model that simultaneously clusters object bounding boxes and pixel level trajectories over time. This approach provides a rich understanding of the motion of objects in the scene. Last, we extend our tracking model for the multi person pose estimation task. We introduce a joint subset partitioning and labelling model where we simultaneously estimate the poses of all the people in the scene. In summary, this thesis addresses a number of diverse tasks that aim to enable vision systems to analyze people in realistic images and videos. In particular, the thesis proposes several novel ideas and rigorous mathematical formulations, pushes the boundary of state-of-the-arts and results in superior performance.

State-of-the-art learning based boundary detection methods require extensive

training data. Since labelling object boundaries is one of the most expensive

types of annotations, there is a need to relax the requirement to carefully

annotate images to make both the training more affordable and to extend the

amount of training data. In this paper we propose a technique to generate

weakly supervised annotations and show that bounding box annotations alone

suffice to reach high-quality object boundaries without using any

object-specific boundary annotations. With the proposed weak supervision

techniques we achieve the top performance on the object boundary detection

task, outperforming by a large margin the current fully supervised

state-of-the-art methods.

Undoing the image formation process and therefore decomposing appearance into

its intrinsic properties is a challenging task due to the under-constraint

nature of this inverse problem. While significant progress has been made on

inferring shape, materials and illumination from images only, progress in an

unconstrained setting is still limited. We propose a convolutional neural

architecture to estimate reflectance maps of specular materials in natural

lighting conditions. We achieve this in an end-to-end learning formulation that

directly predicts a reflectance map from the image itself. We show how to

improve estimates by facilitating additional supervision in an indirect scheme

that first predicts surface orientation and afterwards predicts the reflectance

map by a learning-based sparse data interpolation.

In order to analyze performance on this difficult task, we propose a new

challenge of Specular MAterials on SHapes with complex IllumiNation (SMASHINg)

using both synthetic and real images. Furthermore, we show the application of

our method to a range of image-based editing tasks on real images.

Rotations performed with the index finger and thumb involve some of the most complex motor action among common multi-touch gestures, yet little is known about the factors affecting performance and ergonomics. This note presents results from a study where the angle, direction, diameter, and position of rotations were systematically manipulated. Subjects were asked to perform the rotations as quickly as possible without losing contact with the display, and were allowed to skip rotations that were too uncomfortable. The data show surprising interaction effects among the variables, and help us identify whole categories of rotations that are slow and cumbersome for users.

Clearly explaining a rationale for a classification decision to an end-user

can be as important as the decision itself. Existing approaches for deep visual

recognition are generally opaque and do not output any justification text;

contemporary vision-language models can describe image content but fail to take

into account class-discriminative image aspects which justify visual

predictions. We propose a new model that focuses on the discriminating

properties of the visible object, jointly predicts a class label, and explains

why the predicted label is appropriate for the image. We propose a novel loss

function based on sampling and reinforcement learning that learns to generate

sentences that realize a global sentence property, such as class specificity.

Our results on a fine-grained bird species classification dataset show that our

model is able to generate explanations which are not only consistent with an

image but also more discriminative than descriptions produced by existing

captioning methods.

The goal of this paper is to advance the state-of-the-art of articulated pose

estimation in scenes with multiple people. To that end we contribute on three

fronts. We propose (1) improved body part detectors that generate effective

bottom-up proposals for body parts; (2) novel image-conditioned pairwise terms

that allow to assemble the proposals into a variable number of consistent body

part configurations; and (3) an incremental optimization strategy that explores

the search space more efficiently thus leading both to better performance and

significant speed-up factors. We evaluate our approach on two single-person and

two multi-person pose estimation benchmarks. The proposed approach

significantly outperforms best known multi-person pose estimation results while

demonstrating competitive performance on the task of single person pose

estimation. Models and code available at pose.mpi-inf.mpg.de