Class-Aware Contrastive Semi-Supervised Learning
This work addresses a critical issue in semi-supervised learning for real-world applications with noisy data, offering a drop-in method to enhance model robustness, though it is incremental as it builds on existing SSL frameworks.
The paper tackles the problem of confirmation bias and noisy pseudo-labels in semi-supervised learning, especially with out-of-distribution data, by proposing Class-aware Contrastive Semi-Supervised Learning (CCSSL), which improves pseudo-label quality and robustness, achieving performance gains such as 9.80% over FixMatch and 3.18% over CoMatch on the Semi-iNat 2021 dataset.
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.