Separated and Independent Contrastive Semi-Supervised Learning for Imbalanced Datasets

Conventional semi-supervised learning (SSL) encounters challenges in effectively addressing issues associated with long-tail datasets, primarily stemming from imbalances within a dataset. Existing contrastive SSL methods typically rely on pseudo-labels generated from unlabeled data, which can be inaccurate and introduce confirmation bias toward majority classes. To address this issue, we propose Separated and Independent Contrastive Semi-Supervised Learning (SICSSL), which applies supervised contrastive learning separately and independently to labeled and unlabeled samples. We validate SICSSL on four public benchmark datasets: CIFAR-10-LT, CIFAR-100-LT, STL-10-LT, and ImageNet-127. The results demonstrate consistent performance improvements over existing contrastive learning approaches. Furthermore, SICSSL is modular and easily integrates with recent SSL frameworks, including Auxiliary Balanced Classifier (ABC) and Adaptive Consistency Regularizer (ACR), enabling improved robustness in imbalanced semi-supervised settings. Source code is available at https://github.com/dongyyyyy/SICSSL.