Hard-Soft Pseudo Labels Guided Semi-Supervised Learning for Point Cloud Classification

doi:10.1109/LSP.2024.3386115

CORC > 自动化研究所 > 中国科学院自动化研究所 > 脑图谱与类脑智能实验室 > 脑机接口与融合智能

	Hard-Soft Pseudo Labels Guided Semi-Supervised Learning for Point Cloud Classification
	He, Yuan 4,5; Hu, Guyue 3; Yu, Shan 1,2,5
刊名	IEEE SIGNAL PROCESSING LETTERS
	2024
卷号	31 页码:1059-1063
关键词	Point cloud compression Training Three-dimensional displays Self-supervised learning Semisupervised learning Task analysis Unsupervised learning Point cloud 3D vision semi-supervised learning contrastive learning pseudo label
ISSN号	1070-9908
DOI	10.1109/LSP.2024.3386115
通讯作者	Hu, Guyue(guyue.hu@ahu.edu.cn)
英文摘要	Point clouds are widely applied in 3D visual sensing and perception. However, manually annotating point clouds is much more tedious and time-consuming than that for 2D images. Fortunately, semi-supervised learning can leverage massive unlabeled data to alleviate this issue, which is becoming a promising technique nowadays. In this letter, we propose a novel semi-supervised learning (SSL) framework for point cloud classification, named HPSSL. Its unsupervised learning branch performs both the representation embedding and pseudo-classification tasks. Specifically, both hard and soft pseudo labels of unlabeled samples are generated from a shared classifier to guide the class-aware contrastive learning in our SSL framework. Besides, a prediction consistency strategy is proposed to enhance the discrimination of feature representation and the exactness of pseudo labels. Furthermore, we force the supervised learning branch to interact with the unsupervised learning branch via distribution alignment, thus achieving representation consistency. Extensive experiments on three 3D shape recognition benchmarks demonstrate the effectiveness of the proposed approach.
资助项目	STI 2030-Major Project
WOS关键词	NETWORK
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001204993300002
资助机构	STI 2030-Major Project
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/58688]
专题	脑图谱与类脑智能实验室_脑机接口与融合智能
通讯作者	Hu, Guyue
作者单位	1.Univ Chinese Acad Sci, Sch Future Technol, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Key Lab Brain Cognit & Brain Inspired Intelligence, Beijing 100049, Peoples R China 3.Anhui Univ, Sch Artificial Intelligence, Informat Mat & Intelligent Sensing Lab Anhui Prov, Anhui Prov Key Lab Multimodal Cognit Computat, Hefei 230601, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 5.Chinese Acad Sci, Inst Automat, Lab Brain Atlas & Brain Inspired Intelligence, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	He, Yuan,Hu, Guyue,Yu, Shan. Hard-Soft Pseudo Labels Guided Semi-Supervised Learning for Point Cloud Classification[J]. IEEE SIGNAL PROCESSING LETTERS,2024,31:1059-1063.
APA	He, Yuan,Hu, Guyue,&Yu, Shan.(2024).Hard-Soft Pseudo Labels Guided Semi-Supervised Learning for Point Cloud Classification.IEEE SIGNAL PROCESSING LETTERS,31,1059-1063.
MLA	He, Yuan,et al."Hard-Soft Pseudo Labels Guided Semi-Supervised Learning for Point Cloud Classification".IEEE SIGNAL PROCESSING LETTERS 31(2024):1059-1063.