Harnessing Uncertainty-aware Bounding Boxes for Unsupervised 3D Object Detection

TL;DR

This paper introduces UA3D, an uncertainty-aware framework for unsupervised 3D object detection that reduces the impact of noisy pseudo bounding boxes, leading to significant performance improvements on nuScenes and Lyft datasets.

Contribution

The paper proposes a novel uncertainty estimation and regularization method that enhances unsupervised 3D detection by mitigating pseudo bbox noise effects.

Findings

Improved detection accuracy on nuScenes and Lyft datasets.

Robustness against noisy pseudo bounding boxes.

Significant AP gains compared to existing methods.

Abstract

Unsupervised 3D object detection aims to identify objects of interest from unlabeled raw data, such as LiDAR points. Recent approaches usually adopt pseudo 3D bounding boxes (3D bboxes) from clustering algorithm to initialize the model training. However, pseudo bboxes inevitably contain noise, and such inaccuracies accumulate to the final model, compromising the performance. Therefore, in an attempt to mitigate the negative impact of inaccurate pseudo bboxes, we introduce a new uncertainty-aware framework for unsupervised 3D object detection, dubbed UA3D. In particular, our method consists of two phases: uncertainty estimation and uncertainty regularization. (1) In the uncertainty estimation phase, we incorporate an extra auxiliary detection branch alongside the original primary detector. The prediction disparity between the primary and auxiliary detectors could reflect fine-grained uncertainty at the box coordinate level. (2) Based on the assessed uncertainty, we adaptively adjust the weight of every 3D bbox coordinate via uncertainty regularization, refining the training process on pseudo bboxes. For pseudo bbox coordinate with high uncertainty, we assign a relatively low loss weight. Extensive experiments verify that the proposed method is robust against the noisy pseudo bboxes, yielding substantial improvements on nuScenes and Lyft compared to existing approaches, with increases of +6.9% AP$_{BEV}$ and +2.5% AP$_{3D}$ on nuScenes, and +4.1% AP$_{BEV}$ and +2.0% AP$_{3D}$ on Lyft.