Dengxin Dai (Senior Researcher)

Vision for Autonomous Systems (VAS) Group

My Group Website: VAS

Hiring

  • We are hiring PostDocs, PhD students, and Research Interns; we also offer projects for master's thesis. If you are interested, please contact me <ddai@mpi-inf.mpg.de> with your CV and transcripts. I also accept applicants with CSC scholorship.
  • We focus on deep learning-based perception for autonomous driving, especially on scaling existing visual perception models to novel domains,  to new data modality, to unseen classes and to more tasks 

Publications

2023

  1. Conference paper
    D2
    “Weakly-Supervised Domain Adaptive Semantic Segmentation With Prototypical Contrastive Learning,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada, 2023.
  2. Conference paper
    D2
    “HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada, 2023.
  3. Conference paper
    D2
    “Federated Incremental Semantic Segmentation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada, 2023.
  4. Conference paper
    D2
    “Continuous Pseudo-Label Rectified Domain Adaptive Semantic Segmentation With Implicit Neural Representations,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada, 2023.
  5. Conference paper
    D2
    “MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada, 2023.
  6. Conference paper
    D2D6
    “Self-Supervised Pre-Training With Masked Shape Prediction for 3D Scene Understanding,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), Vancouver, Canada, 2023.
  7. Conference paper
    D2
    “SSB: Simple but Strong Baseline for Boosting Performance of Open-Set Semi-Supervised Learning,” in IEEE/CVF International Conference on Computer Vision (ICCV 2023), Paris, France, 2023.
  8. Conference paper
    D2
    “HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection,” in IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), Bilbao, Spain, 2023.
  9. Conference paper
    D2
    “Test-time Domain Adaptation for Monocular Depth Estimation,” in IEEE International Conference on Robotics and Automation (ICRA 2023), London, UK, 2023.
  10. Conference paper
    D2
    “TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction,” in IEEE International Conference on Robotics and Automation (ICRA 2023), London, UK, 2023.
  11. Article
    D2
    “Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 1, 2023.
  12. Conference paper
    D2
    “Jointly Learning Band Selection and Filter Array Design for Hyperspectral Imaging,” in 2023 IEEE Winter Conference on Applications of Computer Vision (WACV 2023), Waikoloa Village, HI, USA, 2023.
  13. Article
    D2
    “Revisiting Consistency Regularization for Semi-supervised Learning,” International Journal of Computer Vision, vol. 131, 2023.
  14. Article
    D2
    “Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation,” International Journal of Computer Vision, 2023.

2022

  1. Conference paper
    D2
    “Motion Transformer with Global Intention Localization and Local Movement Refinement,” in Advances in Neural Information Processing Systems 35 (NeurIPS 2022), New Orleans, LA, USA, 2022.
  2. Conference paper
    D2
    “TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation,” in Computer Vision -- ECCV 2022, Tel Aviv, Israel, 2022.
  3. Conference paper
    D2
    “Class-Agnostic Object Counting Robust to Intraclass Diversity,” in Computer Vision -- ECCV 2022, Tel Aviv, Israel, 2022.
  4. Conference paper
    D2
    “HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation,” in Computer Vision -- ECCV 2022, Tel Aviv, Israel, 2022.
  5. Conference paper
    D2
    “Pix2NeRF: Unsupervised Conditional Pi-GAN for Single Image to Neural Radiance Fields Translation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.
  6. Conference paper
    D2
    “Decoupling Zero-Shot Semantic Segmentation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.
  7. Conference paper
    D2
    “CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.
  8. Conference paper
    D2
    “Bi-level Alignment for Cross-Domain Crowd Counting,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.
  9. Conference paper
    D2
    “LiDAR Snowfall Simulation for Robust 3D Object Detection,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.
  10. Conference paper
    D2
    “DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.
  11. Conference paper
    D2
    “Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.
  12. Conference paper
    D2
    “Scribble-Supervised LiDAR Semantic Segmentation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.
  13. Conference paper
    D2
    “Sound and Visual Representation Learning with Multiple Pretraining Tasks,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.
  14. Conference paper
    D2
    “Continual Test-Time Domain Adaptation,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.
  15. Conference paper
    D2
    “Adiabatic Quantum Computing for Multi Object Tracking,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.
  16. Article
    D2
    “Multi-Scale Interaction for Real-Time LiDAR Data Segmentation on an Embedded Platform,” IEEE Robotics and Automation Letters, vol. 7, no. 2, 2022.
  17. Article
    D2
    “Improving Depth Estimation Using Map-Based Depth Priors,” IEEE Robotics and Automation Letters, vol. 7, no. 2, 2022.
  18. Article
    D2
    “End-to-End Optimization of LiDAR Beam Configuration for 3D Object Detection and Localization,” IEEE Robotics and Automation Letters, vol. 7, no. 2, 2022.
  19. Article
    D2
    “Learnable Online Graph Representations for 3D Multi-Object Tracking,” IEEE Robotics and Automation Letters, vol. 7, no. 2, 2022.
  20. Conference paper
    D2
    “Hyperspectral Image Super-Resolution with RGB Image Super-Resolution as an Auxiliary Task,” in 2022 IEEE Winter Conference on Applications of Computer Vision (WACV 2022), Waikoloa Village, HI, USA, 2022.
  21. Paper
    D2
    “Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts,” 2022. [Online]. Available: https://arxiv.org/abs/2211.04393.
  22. Paper
    D2
    “Deep Gradient Learning for Efficient Camouflaged Object Detection,” 2022. [Online]. Available: https://arxiv.org/pdf/2205.12853.pdf.
  23. Paper
    D2
    “MTR-A: 1st Place Solution for 2022 Waymo Open Dataset Challenge -- Motion Prediction,” 2022. [Online]. Available: https://arxiv.org/abs/2209.10033.
  24. Paper
    D2
    “Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes,” 2022. [Online]. Available: https://arxiv.org/abs/2208.08621.

2021

  1. Conference paper
    D2
    “mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasets,” in ICCV 2021, IEEE/CVF International Conference on Computer Vision, Virtual Event, 2021.
  2. Conference paper
    D2
    “Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather,” in ICCV 2021, IEEE/CVF International Conference on Computer Vision, Virtual Event, 2021.
  3. Conference paper
    D2
    “ACDC: The Adverse Conditions Dataset with Correspondences for Semantic Driving Scene Understanding,” in ICCV 2021, IEEE/CVF International Conference on Computer Vision, Virtual Event, 2021.
  4. Conference paper
    D2
    “Task Switching Network for Multi-task Learning,” in ICCV 2021, IEEE/CVF International Conference on Computer Vision, Virtual Event, 2021.
  5. Conference paper
    D2
    “Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation,” in ICCV 2021, IEEE/CVF International Conference on Computer Vision, Virtual Event, 2021.
  6. Conference paper
    D2
    “End-to-End Urban Driving by Imitating a Reinforcement Learning Coach,” in ICCV 2021, IEEE/CVF International Conference on Computer Vision, Virtual Event, 2021.
  7. Article
    D2
    “DLOW: Domain Flow and Applications,” International Journal of Computer Vision, vol. 129, 2021.
  8. Paper
    D2
    “TADA: Taxonomy Adaptive Domain Adaptation,” 2021. [Online]. Available: https://arxiv.org/abs/2109.04813.