Publications - Current Year
2024
- “Recent Trends in 3D Reconstruction of General Non-Rigid Scenes,” Computer Graphics Forum (Proc. EUROGRAPHICS 2024), vol. 43.
- “Recent Trends in 3D Reconstruction of General Non-Rigid Scenes,” Computer Graphics Forum (Proc. EUROGRAPHICS 2024), 2024.
- “OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Seattle, WA, USA.
- “Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Seattle, WA, USA.
- “NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Seattle, WA, USA.
- “X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Seattle, WA, USA.
- “Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Seattle, WA, USA.
- “Point Transformer V3: Simpler, Faster, Stronger,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Seattle, WA, USA.
- “Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Seattle, WA, USA.
- “GEARS: Local Geometry-aware Hand-object Interaction Synthesis,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Seattle, WA, USA.
- “Better Understanding Differences in Attribution Methods via Systematic Evaluations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 6, 2024.
- “CosPGD: An Efficient White-Box Adversarial Attack for Pixel-Wise Prediction Tasks,” in Proceedings of the 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria.
- “Implicit Representations for Constrained Image Segmentation,” in Proceedings of the 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria.
- “MultiMax: Sparse and Mulit-Modal Attention Learning,” in Proceedings of the 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria.
- “Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive,” in The Twelfth International Conference on Learning Representations (ICLR 2024), Vienna, Austria, 2024.
- “As large as it gets - Studying Infinitely Large Convolutions via Neural Implicit Frequency Filters,” Transactions on Machine Learning Research, vol. 2024, 2024.
- “Towards Designing Inherently Interpretable Deep Neural Networks for Image Classification,” Universität des Saarlandes, Saarbrücken, 2024.
- “Good Teachers Explain: Explanation-Enhanced Knowledge Distillation,” 2024. [Online]. Available: https://arxiv.org/abs/2402.03119.mehr
Abstract
Knowledge Distillation (KD) has proven effective for compressing large
teacher models into smaller student models. While it is well known that student
models can achieve similar accuracies as the teachers, it has also been shown
that they nonetheless often do not learn the same function. It is, however,
often highly desirable that the student's and teacher's functions share similar
properties such as basing the prediction on the same input features, as this
ensures that students learn the 'right features' from the teachers. In this
work, we explore whether this can be achieved by not only optimizing the
classic KD loss but also the similarity of the explanations generated by the
teacher and the student. Despite the idea being simple and intuitive, we find
that our proposed 'explanation-enhanced' KD (e$^2$KD) (1) consistently provides
large gains in terms of accuracy and student-teacher agreement, (2) ensures
that the student learns from the teacher to be right for the right reasons and
to give similar explanations, and (3) is robust with respect to the model
architectures, the amount of training data, and even works with 'approximate',
pre-computed explanations.