Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection

TL;DR

This paper introduces a novel unsupervised domain adaptation method for 3D object detection in autonomous driving, using pseudo-labels generated from replays of recorded sequences to improve detection accuracy in new environments.

Contribution

It proposes a new fine-tuning approach that leverages future information in replays to generate pseudo-labels, significantly reducing domain gap and enhancing detection performance.

Findings

Substantial accuracy improvements across five datasets

Effective reduction of domain gap in new environments

Enhanced detection reliability in autonomous driving scenarios

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.