Semi-supervised 3D Object Detection via Adaptive Pseudo-Labeling

TL;DR

This paper introduces a semi-supervised framework for outdoor 3D object detection that leverages adaptive pseudo-labeling and data augmentation to reduce annotation costs and improve detection robustness.

Contribution

It proposes the ACCS module for high-quality pseudo-label generation and HPCA for data augmentation, advancing semi-supervised 3D detection methods.

Findings

Effective pseudo-labels improve detection accuracy

Data augmentation enhances robustness in unlabeled data

Method outperforms existing semi-supervised approaches on KITTI

Abstract

3D object detection is an important task in computer vision. Most existing methods require a large number of high-quality 3D annotations, which are expensive to collect. Especially for outdoor scenes, the problem becomes more severe due to the sparseness of the point cloud and the complexity of urban scenes. Semi-supervised learning is a promising technique to mitigate the data annotation issue. Inspired by this, we propose a novel semi-supervised framework based on pseudo-labeling for outdoor 3D object detection tasks. We design the Adaptive Class Confidence Selection module (ACCS) to generate high-quality pseudo-labels. Besides, we propose Holistic Point Cloud Augmentation (HPCA) for unlabeled data to improve robustness. Experiments on the KITTI benchmark demonstrate the effectiveness of our method.