Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gaps (2403.17633v4)

Published 26 Mar 2024 in cs.CV, cs.AI, and cs.RO

Abstract: In this study, we address a gap in existing unsupervised domain adaptation approaches on LiDAR-based 3D object detection, which have predominantly concentrated on adapting between established, high-density autonomous driving datasets. We focus on sparser point clouds, capturing scenarios from different perspectives: not just from vehicles on the road but also from mobile robots on sidewalks, which encounter significantly different environmental conditions and sensor configurations. We introduce Unsupervised Adversarial Domain Adaptation for 3D Object Detection (UADA3D). UADA3D does not depend on pre-trained source models or teacher-student architectures. Instead, it uses an adversarial approach to directly learn domain-invariant features. We demonstrate its efficacy in various adaptation scenarios, showing significant improvements in both self-driving car and mobile robot domains. Our code is open-source and will be available soon.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (67)
  1. Transfusion: Robust lidar-camera fusion for 3d object detection with transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1090–1099, 2022.
  2. nuscenes: A multimodal dataset for autonomous driving. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11621–11631, 2020.
  3. Domain adaptive faster r-cnn for object detection in the wild. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3339–3348, 2018.
  4. Revisiting domain-adaptive 3d object detection by reliable, diverse and class-balanced pseudo-labeling. In Proceedings of the International Conference on Computer Vision, pages 3714–3726, 2023.
  5. Adversarial training on point clouds for sim-to-real 3d object detection. IEEE Robotics and Automation Letters, 6(4):6662–6669, 2021.
  6. Lidar-cs dataset: Lidar point cloud dataset with cross-sensors for 3d object detection. arXiv preprint arXiv:2301.12515, 2023.
  7. Open compound domain adaptation with object style compensation for semantic segmentation. Advances in Neural Information Processing Systems, 36, 2024.
  8. Y. Ganin and V. Lempitsky. Unsupervised domain adaptation by backpropagation. In International Conference on Machine Learning, pages 1180–1189. PMLR, 2015.
  9. Vision meets robotics: The kitti dataset. The International Journal of Robotics Research, 2013.
  10. Structure aware single-stage 3d object detection from point cloud. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11873–11882, 2020.
  11. Z. He and L. Zhang. Multi-adversarial faster-rcnn for unrestricted object detection. In Proceedings of the International Conference on Computer Vision, pages 6668–6677, 2019.
  12. Uncertainty-aware mean teacher for source-free unsupervised domain adaptive 3d object detection. arXiv preprint arXiv:2109.14651, 2021.
  13. Cycada: Cycle-consistent adversarial domain adaptation. In International Conference on Machine Learning, pages 1989–1998. Pmlr, 2018.
  14. Density-insensitive unsupervised domain adaption on 3d object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 17556–17566, 2023.
  15. Soap: Cross-sensor domain adaptation for 3d object detection using stationary object aggregation pseudo-labelling. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 3352–3361, 2024.
  16. Monodtr: Monocular 3d object detection with depth-aware transformer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4012–4021, 2022.
  17. xmuda: Cross-modal unsupervised domain adaptation for 3d semantic segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12605–12614, 2020.
  18. D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  19. Conda: Unsupervised domain adaptation for lidar segmentation via regularized domain concatenation. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 9338–9345. IEEE, 2023.
  20. Pointpillars: Fast encoders for object detection from point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12697–12705, 2019.
  21. Sustech points: A portable 3d point cloud interactive annotation platform system. In 2020 IEEE Intelligent Vehicles Symposium (IV), pages 1108–1115, 2020.
  22. Domain adaptive object detection for autonomous driving under foggy weather. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 612–622, 2023.
  23. Model adaptation: Unsupervised domain adaptation without source data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9641–9650, 2020.
  24. Gpa-3d: Geometry-aware prototype alignment for unsupervised domain adaptive 3d object detection from point clouds. In Proceedings of the International Conference on Computer Vision, pages 6394–6403, 2023.
  25. Bevfusion: A simple and robust lidar-camera fusion framework. Advances in Neural Information Processing Systems, 35:10421–10434, 2022.
  26. Geometry-aware network for domain adaptive semantic segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 8755–8763, 2023.
  27. Adversarial unsupervised domain adaptation with conditional and label shift: Infer, align and iterate. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10367–10376, 2021.
  28. Bevfusion: Multi-task multi-sensor fusion with unified bird’s-eye view representation. In Proceedings of the IEEE International Conference on Robotics and Automation, pages 2774–2781. IEEE, 2023.
  29. Unsupervised domain adaptive 3d detection with multi-level consistency. In Proceedings of the International Conference on Computer Vision, pages 8866–8875, 2021.
  30. Mcd: Diverse large-scale multi-campus dataset for robot perception. arXiv preprint arXiv:2403.11496, 2024.
  31. Frustum-pointpillars: A multi-stage approach for 3d object detection using rgb camera and lidar. In Proceedings of the International Conference on Computer Vision, pages 2926–2933, 2021.
  32. Cl3d: Unsupervised domain adaptation for cross-lidar 3d detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 2047–2055, 2023.
  33. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 652–660, 2017.
  34. Strong-weak distribution alignment for adaptive object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6956–6965, 2019.
  35. Sf-uda 3d: Source-free unsupervised domain adaptation for lidar-based 3d object detection. In Proceedings of the International Conference on 3D Vision (3DV), pages 771–780. IEEE, 2020.
  36. Night-to-day: Online image-to-image translation for object detection within autonomous driving by night. IEEE Transactions on Intelligent Vehicles, 6(3):480–489, 2021.
  37. Pointrcnn: 3d object proposal generation and detection from point cloud. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 770–779, 2019.
  38. Introduction to autonomous mobile robots. MIT press, 2011.
  39. Scalability in perception for autonomous driving: Waymo open dataset. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2446–2454, 2020.
  40. O. D. Team. Openpcdet: An open-source toolbox for 3d object detection from point clouds. https://github.com/open-mmlab/OpenPCDet, 2020.
  41. Mapless lidar navigation control of wheeled mobile robots based on deep imitation learning. IEEE Access, 9:117527–117541, 2021.
  42. Ms3d: Leveraging multiple detectors for unsupervised domain adaptation in 3d object detection. In International Conference on Intelligent Transportation Systems. IEEE, 2023.
  43. See eye to eye: A lidar-agnostic 3d detection framework for unsupervised multi-target domain adaptation. IEEE Robotics and Automation Letters, 7(3):7904–7911, 2022.
  44. V. Vidit and M. Salzmann. Attention-based domain adaptation for single-stage detectors. Machine Vision and Applications, 33(5):1–14, 2022.
  45. Towards online domain adaptive object detection. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pages 478–488, 2023.
  46. Advent: Adversarial entropy minimization for domain adaptation in semantic segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2517–2526, 2019.
  47. Monocular 3d object detection with depth from motion. In Proceedings of the European Conference on Computer Vision, pages 386–403. Springer, 2022.
  48. Train in germany, test in the usa: Making 3d object detectors generalize. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11710–11720, 2020.
  49. Ssda3d: Semi-supervised domain adaptation for 3d object detection from point cloud. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 2707–2715, 2023.
  50. Unsupervised subcategory domain adaptive network for 3d object detection in lidar. Electronics, 10(8):927, 2021.
  51. Lidar distillation: Bridging the beam-induced domain gap for 3d object detection. In Proceedings of the European Conference on Computer Vision, pages 179–195. Springer, 2022.
  52. Argoverse 2: Next generation datasets for self-driving perception and forecasting. In NeurIPS, 2021.
  53. Applying 3d object detection from self-driving cars to mobile robots: A survey and experiments. In 2023 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), pages 3–9. IEEE, 2023.
  54. Towards a robust sensor fusion step for 3d object detection on corrupted data. IEEE Robotics and Automation Letters, 2023.
  55. Exploring categorical regularization for domain adaptive object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11724–11733, 2020.
  56. Spg: Unsupervised domain adaptation for 3d object detection via semantic point generation. In Proceedings of the International Conference on Computer Vision, pages 15446–15456, 2021.
  57. Second: Sparsely embedded convolutional detection. Sensors, 18(10):3337, 2018.
  58. St3d: Self-training for unsupervised domain adaptation on 3d object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10368–10378, 2021.
  59. St3d++: Denoised self-training for unsupervised domain adaptation on 3d object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5):6354–6371, 2022.
  60. 3dssd: Point-based 3d single stage object detector. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11040–11048, 2020.
  61. Std: Sparse-to-dense 3d object detector for point cloud. In Proceedings of the International Conference on Computer Vision, pages 1951–1960, 2019.
  62. Complete & label: A domain adaptation approach to semantic segmentation of lidar point clouds. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 15363–15373, 2021.
  63. Center-based 3d object detection and tracking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11784–11793, 2021.
  64. Bi3d: Bi-domain active learning for cross-domain 3d object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15599–15608, 2023.
  65. Joint distribution alignment via adversarial learning for domain adaptive object detection. IEEE Transactions on Multimedia, 24:4102–4112, 2021.
  66. Not all points are equal: Learning highly efficient point-based detectors for 3d lidar point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 18953–18962, 2022.
  67. Y. Zhou and O. Tuzel. Voxelnet: End-to-end learning for point cloud based 3d object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4490–4499, 2018.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Mattias Hansson (1 paper)
  2. Marko Thiel (15 papers)
  3. Patric Jensfelt (48 papers)
  4. Maciej K Wozniak (3 papers)
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets