Title | Class-Aware Contrastive Semi-Supervised Learning |
Author | |
Corresponding Author | Feng 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 Type | Conference paper |
Identifier | http://kc.sustech.edu.cn/handle/2SGJ60CL/415791 |
Department | Department 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 Affilication | Southern 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. |
|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment