Class-Aware Contrastive Semi-Supervised Learning

Fan Yang2; Kai Wu1; Shuyi Zhang1; Guannan Jiang4; Yong Liu1; Feng Zheng3; Wei Zhang4; Chengjie Wang1; Long Zeng2

10.1109/CVPR52688.2022.01402

2022

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

1063-6919

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)

JUN 18-24, 2022

null,New Orleans,LA

10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA

IEEE COMPUTER SOC

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.

Corresponding

English

CPCI-S

Computer Science ; Imaging Science & Photographic Technology

Computer Science, Artificial Intelligence ; Imaging Science & Photographic Technology

WOS:000870759107049

Web of Science

1.Tencent Youtu Lab
2.Tsinghua University
3.Southern University of Science and Technology, China
4.CATL

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.