# Recurrent Contrastive Learning for Imbalanced Medical Image Classification

arXiv: https://arxiv.org/abs/2608.03304 · HTML: https://mlsanity.com/paper/2608.03304/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [Balanced Contrastive Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2207.09052/) (2022)
- [DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data](https://mlsanity.com/paper/2105.02340/) (2021)
- [HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image Classification](https://mlsanity.com/paper/2209.10218/) (2022)
- [ProCo: Prototype-aware Contrastive Learning for Long-tailed Medical Image Classification](https://mlsanity.com/paper/2209.00183/) (2022)
- [Learning from Neighbors: Category Extrapolation for Long-Tail Learning](https://mlsanity.com/paper/2410.15980/) (2024)
- [ECL: Class-Enhancement Contrastive Learning for Long-tailed Skin Lesion Classification](https://mlsanity.com/paper/2307.04136/) (2023)
- [Hierarchical Corpus-View-Category Refinement for Carotid Plaque Risk Grading in Ultrasound](https://mlsanity.com/paper/2506.23108/) (2025)
- [Similarity Memory Prior is All You Need for Medical Image Segmentation](https://mlsanity.com/paper/2507.00585/) (2025)
- [Equilibrium contrastive learning for imbalanced image classification](https://mlsanity.com/paper/2602.09506/) (2026)

## Abstract (arXiv)

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.