中文版 | English
Title

Class-Aware Contrastive Semi-Supervised Learning

Author
Corresponding AuthorFeng Zheng; Chengjie Wang
DOI
Publication Years
2022
Conference Name
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
ISSN
1063-6919
Source Title
Conference Date
JUN 18-24, 2022
Conference Place
null,New Orleans,LA
Publication Place
10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA
Publisher
Abstract
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover, the model's judgment becomes noisier in real-world applications with extensive out-of-distribution data. To address this issue, we propose a general method named Class-aware Contrastive Semi-Supervised Learning (CCSSL), which is a drop-in helper to improve the pseudo-label quality and enhance the model's robustness in the real-world setting. Rather than treating real-world data as a union set, our method separately handles reliable in-distribution data with class-wise clustering for blending into downstream tasks and noisy out-of-distribution data with image-wise contrastive for better generalization. Furthermore, by applying target reweighting, we successfully emphasize clean label learning and simultaneously reduce noisy label learning. Despite its simplicity, our proposed CCSSL has significant performance improvements over the state-of-the-art SSL methods on the standard datasets CIFAR100 [18] and STL10 [8]. On the real-world dataset Semi-iNat 2021 [27], we improve FixMatch [25] by 9.80% and CoMatch [19] by 3.18%. Code is available https://github.com/TencentYoutuResearch/Classification-SemiCLS.
SUSTech Authorship
Corresponding
Language
English
URL[Source Record]
Indexed By
WOS Research Area
Computer Science ; Imaging Science & Photographic Technology
WOS Subject
Computer Science, Artificial Intelligence ; Imaging Science & Photographic Technology
WOS Accession No
WOS:000870759107049
Data Source
Web of Science
Citation statistics
Cited Times [WOS]:1
Document TypeConference paper
Identifierhttp://kc.sustech.edu.cn/handle/2SGJ60CL/415791
DepartmentDepartment of Computer Science and Engineering
Affiliation
1.Tencent Youtu Lab
2.Tsinghua University
3.Southern University of Science and Technology, China
4.CATL
Corresponding Author AffilicationSouthern University of Science and Technology
Recommended Citation
GB/T 7714
Fan Yang,Kai Wu,Shuyi Zhang,et al. Class-Aware Contrastive Semi-Supervised Learning[C]. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA:IEEE COMPUTER SOC,2022.
Files in This Item:
There are no files associated with this item.
Related Services
Fulltext link
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Export to Excel
Export to Csv
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Fan Yang]'s Articles
[Kai Wu]'s Articles
[Shuyi Zhang]'s Articles
Baidu Scholar
Similar articles in Baidu Scholar
[Fan Yang]'s Articles
[Kai Wu]'s Articles
[Shuyi Zhang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Fan Yang]'s Articles
[Kai Wu]'s Articles
[Shuyi Zhang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.