Detecting 3D objects from point clouds is a practical yet challenging task that has attracted increasing attention recently. In this paper, we propose a Label-Guided auxiliary training method for 3D object detection (LG3D), which serves as an auxiliary network to enhance the feature learning of existing 3D object detectors. Specifically, we propose two novel modules: a Label-Annotation-Inducer that maps annotations and point clouds in bounding boxes to task-specific representations and a Label-Knowledge-Mapper that assists the original features to obtain detection-critical representations. The proposed auxiliary network is discarded in inference and thus has no extra computational cost at test time. We conduct extensive experiments on both indoor and outdoor datasets to verify the effectiveness of our approach. For example, our proposed LG3D improves VoteNet by 2.5% and 3.1% mAP on the SUN RGB-D and ScanNetV2 datasets, respectively.
@article{arxiv.2207.11753,
title = {Label-Guided Auxiliary Training Improves 3D Object Detector},
author = {Yaomin Huang and Xinmei Liu and Yichen Zhu and Zhiyuan Xu and Chaomin Shen and Zhengping Che and Guixu Zhang and Yaxin Peng and Feifei Feng and Jian Tang},
journal= {arXiv preprint arXiv:2207.11753},
year = {2022}
}
Comments
Yaomin Huang and Xinmei Liu are with equal contribution. This paper has been accepted by ECCV 2022