English

Class-Aware Contrastive Semi-Supervised Learning

Computer Vision and Pattern Recognition 2022-09-12 v3

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 re-weighting, 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 and STL10. On the real-world dataset Semi-iNat 2021, we improve FixMatch by 9.80% and CoMatch by 3.18%. Code is available https://github.com/TencentYoutuResearch/Classification-SemiCLS.

Keywords

Cite

@article{arxiv.2203.02261,
  title  = {Class-Aware Contrastive Semi-Supervised Learning},
  author = {Fan Yang and Kai Wu and Shuyi Zhang and Guannan Jiang and Yong Liu and Feng Zheng and Wei Zhang and Chengjie Wang and Long Zeng},
  journal= {arXiv preprint arXiv:2203.02261},
  year   = {2022}
}

Comments

cvpr2022 accepted, half more page for adding rebuttal Infos

R2 v1 2026-06-24T10:02:00.690Z