FAST3D: Flow-Aware Self-Training for 3D Object Detectors

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors. This eliminates the need for expensive, high-quality labels whenever the environment changes (e.g., geographic location, sensor setup, weather condition). State-of-the-art self-training approaches, however, mostly ignore the temporal nature of autonomous driving data. To address this issue, we propose a flow-aware self-training method that enables unsupervised domain adaptation for 3D object detectors on continuous LiDAR point clouds. In order to get reliable pseudo-labels, we leverage scene flow to propagate detections through time. In particular, we introduce a flow-based multi-target tracker, that exploits flow consistency to filter and refine resulting tracks. The emerged precise pseudo-labels then serve as a basis for model re-training. Starting with a pre-trained KITTI model, we conduct experiments on the challenging Waymo Open Dataset to demonstrate the effectiveness of our approach. Without any prior target domain knowledge, our results show a significant improvement over the state-of-the-art.
Original languageEnglish
Title of host publicationBritish Machine Vision Conference (BMVC) 2021
PublisherThe British Machine Vision Association
Number of pages14
Publication statusPublished - 23 Nov 2021
Event32nd British Machine Vision Conference: BMVC 2021 - Virtuell, United Kingdom
Duration: 22 Nov 202125 Nov 2021

Conference

Conference32nd British Machine Vision Conference
Abbreviated titleBMVC 2021
Country/TerritoryUnited Kingdom
CityVirtuell
Period22/11/2125/11/21

Cite this