Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection
arXiv:2103.14198
Abstract
Self-driving cars must detect other vehicles and pedestrians in 3D to plan safe routes and avoid collisions. State-of-the-art 3D object detectors, based on deep learning, have shown promising accuracy but are prone to over-fit to domain idiosyncrasies, making them fail in new environments -- a serious problem if autonomous vehicles are meant to operate freely. In this paper, we propose a novel learning approach that drastically reduces this gap by fine-tuning the detector on pseudo-labels in the target domain, which our method generates while the vehicle is parked, based on replays of previously recorded driving sequences. In these replays, objects are tracked over time, and detections are interpolated and extrapolated -- crucially, leveraging future information to catch hard cases. We show, on five autonomous driving datasets, that fine-tuning the object detector on these pseudo-labels substantially reduces the domain gap to new driving environments, yielding drastic improvements in accuracy and detection reliability.
arXiv commentAccepted by ICRA 2022
References in corpus (6)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
- Scalability in Perception for Autonomous Driving: Waymo Open Dataset
- PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation
- Center-based 3D Object Detection and Tracking
- Probabilistic 3D Multi-Object Tracking for Autonomous Driving