Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features
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.
Code (1)
Tasks
3D Object DetectionDomain Adaptationobject-detectionObject DetectionSelf-Driving CarsUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Unsupervised Adaptation from Repeated Traversals for Autonomous Driving
For a self-driving car to operate reliably, its perceptual system must generalize to the end-user's environment -- ideally without additional annotation efforts. One potential solution is to leverage unlabeled data (e.g.…
3D Object DetectionAutonomous DrivingDomain Adaptationobject-detection+2CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars
Although unsupervised domain adaptation methods have achieved remarkable performance in semantic scene segmentation in visual perception for self-driving cars, these approaches remain impractical in real-world use cases.…
Domain AdaptationScene SegmentationSegmentationSelf-Driving Cars+1Unsupervised Domain Adaptation in Semantic Segmentation Based on Pixel Alignment and Self-Training
This paper proposes an unsupervised cross-modality domain adaptation approach based on pixel alignment and self-training. Pixel alignment transfers ceT1 scans to hrT2 modality, helping to reduce domain shift in the train…
Domain AdaptationSegmentationSemantic SegmentationUnsupervised Domain AdaptationUADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gaps
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 dri…
3D Object DetectionAutonomous DrivingDomain Adaptationobject-detection+2ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation
Transferring knowledge learned from the labeled source domain to the raw target domain for unsupervised domain adaptation (UDA) is essential to the scalable deployment of autonomous driving systems. State-of-the-art meth…
Autonomous DrivingDomain AdaptationLIDAR Semantic SegmentationSemantic Segmentation+1