Recurrent Contrastive Learning for Imbalanced Medical Image Classification

2026-08-04

AI Summary

This work addresses the challenge of class imbalance in medical image classification, where tail classes often exhibit compact representations that are easily dominated by head classes, leading to biased decision boundaries. To mitigate this issue, the authors propose a recursive contrastive learning framework that leverages a temporal memory queue and a temporal anchor mechanism to construct an anchor field for tail classes. By iteratively reusing historical feature states during training, the method progressively expands the latent support region of tail classes, thereby enhancing inter-class separability. Built upon the DINOv3 backbone with LoRA adapters for feature extraction, the approach demonstrates significant performance gains over strong baselines across three imbalanced medical imaging datasets, confirming its effectiveness and robustness.

Abstract

Medical image classification often suffers from class imbalance due to the inherent disparities in disease incidence. Existing approaches, such as class resampling and loss reweighting, mainly improve learning within the observed feature distribution, but do not explicitly enlarge the latent support region of tail classes. As a result, tail-class representations remain overly compact and are easily encroached upon by head classes, leading to biased decision boundaries. In this work, we propose Recurrent Contrastive Learning (RCL) for imbalanced medical image classification. RCL progressively expands the support region of tail classes by recurrently reusing historical feature states across training phases. Specifically, we adopt DINOv3 with LoRA adapters as the backbone to provide robust feature embeddings. We then devise a Temporal Memory Queue (TMQ) to preserve corpus-level features across training phases and provide diversified global references for contrastive learning. Based on TMQ, we construct Temporal Anchors (TARs) to form an anchor field around tail classes. This field enlarges the support region of tail classes, suppresses head-class encroachment, and improves inter-class separation. Extensive experiments on three imbalanced medical datasets demonstrate that RCL achieves consistent improvements over strong baselines. The code is available at https://github.com/dndins/RCL.

Problem

• class imbalance
• medical image classification
• tail classes
• decision boundary bias
• feature representation

Innovation

• Recurrent Contrastive Learning
• Temporal Memory Queue
• Temporal Anchors
• Imbalanced Medical Image Classification
• Tail-class Support Expansion