STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learning

TL;DR

STAL3D introduces a novel unsupervised domain adaptation framework combining self-training and adversarial learning to improve 3D object detection across different domains, effectively addressing domain gaps and background interference.

Contribution

The paper proposes STAL3D, a new framework that integrates self-training and adversarial learning with modules tailored for 3D scenes, achieving state-of-the-art results in cross-domain 3D detection.

Findings

Achieves state-of-the-art performance on multiple cross-domain tasks.

Surpasses Oracle results on Waymo to KITTI and Waymo to KITTI-rain tasks.

Effectively alleviates background interference and size bias issues.

Abstract

Existing 3D object detection suffers from expensive annotation costs and poor transferability to unknown data due to the domain gap, Unsupervised Domain Adaptation (UDA) aims to generalize detection models trained in labeled source domains to perform robustly on unexplored target domains, providing a promising solution for cross-domain 3D object detection. Although Self-Training (ST) based cross-domain 3D detection methods with the assistance of pseudo-labeling techniques have achieved remarkable progress, they still face the issue of low-quality pseudo-labels when there are significant domain disparities due to the absence of a process for feature distribution alignment. While Adversarial Learning (AL) based methods can effectively align the feature distributions of the source and target domains, the inability to obtain labels in the target domain forces the adoption of asymmetric optimization losses, resulting in a challenging issue of source domain bias. To overcome these limitations, we propose a novel unsupervised domain adaptation framework for 3D object detection via collaborating ST and AL, dubbed as STAL3D, unleashing the complementary advantages of pseudo labels and feature distribution alignment. Additionally, a Background Suppression Adversarial Learning (BS-AL) module and a Scale Filtering Module (SFM) are designed tailored for 3D cross-domain scenes, effectively alleviating the issues of the large proportion of background interference and source domain size bias. Our STAL3D achieves state-of-the-art performance on multiple cross-domain tasks and even surpasses the Oracle results on Waymo $\rightarrow$ KITTI and Waymo $\rightarrow$ KITTI-rain.