Unsupervised Object Detection with LiDAR Clues

TL;DR

This paper introduces a novel unsupervised object detection method that leverages LiDAR clues and 3D scene structure to improve localization and handle diverse object categories, achieving promising results on the Waymo dataset.

Contribution

It presents the first practical approach combining 2D images and 3D LiDAR data for unsupervised object detection, addressing boundary ambiguity and long-tailed distributions.

Findings

Achieves reasonable accuracy compared to supervised methods within LiDAR range.

Effectively mitigates boundary ambiguity using 3D scene structure.

Handles long-tailed and open-ended category distributions.

Abstract

Despite the importance of unsupervised object detection, to the best of our knowledge, there is no previous work addressing this problem. One main issue, widely known to the community, is that object boundaries derived only from 2D image appearance are ambiguous and unreliable. To address this, we exploit LiDAR clues to aid unsupervised object detection. By exploiting the 3D scene structure, the issue of localization can be considerably mitigated. We further identify another major issue, seldom noticed by the community, that the long-tailed and open-ended (sub-)category distribution should be accommodated. In this paper, we present the first practical method for unsupervised object detection with the aid of LiDAR clues. In our approach, candidate object segments based on 3D point clouds are firstly generated. Then, an iterative segment labeling process is conducted to assign segment labels and to train a segment labeling network, which is based on features from both 2D images and 3D point clouds. The labeling process is carefully designed so as to mitigate the issue of long-tailed and open-ended distribution. The final segment labels are set as pseudo annotations for object detection network training. Extensive experiments on the large-scale Waymo Open dataset suggest that the derived unsupervised object detection method achieves reasonable accuracy compared with that of strong supervision within the LiDAR visible range. Code shall be released.