Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Class-Aware Contrastive Semi-Supervised Learning

About

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.

Fan Yang, Kai Wu, Shuyi Zhang, Guannan Jiang, Yong Liu, Feng Zheng, Wei Zhang, Chengjie Wang, Long Zeng• 2022

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-100 (test)
Accuracy71.13
3518
Image ClassificationCIFAR-10 (test)
Accuracy88.77
3381
Image ClassificationCIFAR10 (test)
Accuracy95.54
585
Image ClassificationSUN397--
425
Image ClassificationDTD
Accuracy72.7
419
Image ClassificationCIFAR100 (test)
Top-1 Accuracy80.68
377
Image ClassificationSTL-10 (test)
Accuracy82
357
Image ClassificationCIFAR-100--
302
Image ClassificationSVHN (test)
Accuracy88.6
199
Image ClassificationCaltech-101--
146
Showing 10 of 23 rows

Other info

Code

Follow for update