Label-Guided Auxiliary Training Improves 3D Object Detector

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 exis...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Huang, Yaomin, Liu, Xinmei, Zhu, Yichen, Xu, Zhiyuan, Shen, Chaomin, Che, Zhengping, Zhang, Guixu, Peng, Yaxin, Feng, Feifei, Tang, Jian
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 24.07.2022
Subjects
Annotations
Datasets
Knowledge representation
Object recognition
Three dimensional models
Training
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422