Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection

TL;DR

This paper introduces a pseudo label refinery framework for unsupervised domain adaptation in 3D object detection, enhancing pseudo label reliability through augmentation and proposal generation, leading to improved performance across benchmarks.

Contribution

The proposed method refines pseudo labels using complementary augmentation and proposal alignment, significantly improving 3D UDA performance over existing techniques.

Findings

Outperforms state-of-the-art on six benchmarks

Improves pseudo label quality through augmentation strategies

Enhances domain adaptation in 3D object detection

Abstract

Recent self-training techniques have shown notable improvements in unsupervised domain adaptation for 3D object detection (3D UDA). These techniques typically select pseudo labels, i.e., 3D boxes, to supervise models for the target domain. However, this selection process inevitably introduces unreliable 3D boxes, in which 3D points cannot be definitively assigned as foreground or background. Previous techniques mitigate this by reweighting these boxes as pseudo labels, but these boxes can still poison the training process. To resolve this problem, in this paper, we propose a novel pseudo label refinery framework. Specifically, in the selection process, to improve the reliability of pseudo boxes, we propose a complementary augmentation strategy. This strategy involves either removing all points within an unreliable box or replacing it with a high-confidence box. Moreover, the point numbers of instances in high-beam datasets are considerably higher than those in low-beam datasets, also degrading the quality of pseudo labels during the training process. We alleviate this issue by generating additional proposals and aligning RoI features across different domains. Experimental results demonstrate that our method effectively enhances the quality of pseudo labels and consistently surpasses the state-of-the-art methods on six autonomous driving benchmarks. Code will be available at https://github.com/Zhanwei-Z/PERE.