UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gaps

TL;DR

This paper introduces UADA3D, an unsupervised adversarial domain adaptation method that improves 3D object detection in sparse LiDAR data across diverse environments without relying on pre-trained models.

Contribution

UADA3D is a novel unsupervised adversarial approach that directly learns domain-invariant features for 3D detection without pre-trained source models or teacher-student setups.

Findings

Significant performance improvements in domain adaptation scenarios.

Effective in both autonomous driving and mobile robot environments.

Operates without pre-trained source models.

Abstract

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 driving datasets. We focus on sparser point clouds, capturing scenarios from different perspectives: not just from vehicles on the road but also from mobile robots on sidewalks, which encounter significantly different environmental conditions and sensor configurations. We introduce Unsupervised Adversarial Domain Adaptation for 3D Object Detection (UADA3D). UADA3D does not depend on pre-trained source models or teacher-student architectures. Instead, it uses an adversarial approach to directly learn domain-invariant features. We demonstrate its efficacy in various adaptation scenarios, showing significant improvements in both self-driving car and mobile robot domains. Our code is open-source and will be available soon.