Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features

Travis Zhang, Katie Luo, Cheng Perng Phoo, Yurong You, Wei-Lun Chao, Bharath Hariharan, Mark Campbell, Kilian Q. Weinberger; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2023, pp. 4040-4046


The rapid development of 3D object detection systems for self-driving cars has significantly improved accuracy. However, these systems struggle to generalize across diverse driving environments, which can lead to safety-critical failures in detecting traffic participants. To address this, we propose a method that utilizes unlabeled repeated traversals of multiple locations to adapt object detectors to new driving environments. By incorporating statistics computed from repeated LiDAR scans, we guide the adaptation process effectively. Our approach enhances LiDAR-based detection models using spatial quantized historical features and introduces a lightweight regression head to leverage the statistics for feature regularization. Additionally, we leverage the statistics for a novel self-training process to stabilize the training. The framework is detector model-agnostic and experiments on real-world datasets demonstrate significant improvements, achieving up to a 20-point performance gain, especially in detecting pedestrians and distant objects. Code is available at https://github.com/zhangtravis/Hist-DA.

Related Material

[pdf] [arXiv]
@InProceedings{Zhang_2023_ICCV, author = {Zhang, Travis and Luo, Katie and Phoo, Cheng Perng and You, Yurong and Chao, Wei-Lun and Hariharan, Bharath and Campbell, Mark and Weinberger, Kilian Q.}, title = {Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2023}, pages = {4040-4046} }