CLAF: Contrastive Learning with Augmented Features for Imbalanced Semi-Supervised Learning
This addresses the challenge of imbalanced data in semi-supervised learning for applications like image classification, though it is incremental as it builds on existing contrastive and semi-supervised methods.
The paper tackles the problem of imbalanced data in semi-supervised learning, where pseudo-labels bias toward majority classes, by proposing CLAF, which uses class-dependent feature augmentation and contrastive loss with labeled data, achieving improved performance on imbalanced image classification datasets.
Due to the advantages of leveraging unlabeled data and learning meaningful representations, semi-supervised learning and contrastive learning have been progressively combined to achieve better performances in popular applications with few labeled data and abundant unlabeled data. One common manner is assigning pseudo-labels to unlabeled samples and selecting positive and negative samples from pseudo-labeled samples to apply contrastive learning. However, the real-world data may be imbalanced, causing pseudo-labels to be biased toward the majority classes and further undermining the effectiveness of contrastive learning. To address the challenge, we propose Contrastive Learning with Augmented Features (CLAF). We design a class-dependent feature augmentation module to alleviate the scarcity of minority class samples in contrastive learning. For each pseudo-labeled sample, we select positive and negative samples from labeled data instead of unlabeled data to compute contrastive loss. Comprehensive experiments on imbalanced image classification datasets demonstrate the effectiveness of CLAF in the context of imbalanced semi-supervised learning.