English

Flexible Sampling for Long-tailed Skin Lesion Classification

Computer Vision and Pattern Recognition 2025-05-29 v2

Abstract

Most of the medical tasks naturally exhibit a long-tailed distribution due to the complex patient-level conditions and the existence of rare diseases. Existing long-tailed learning methods usually treat each class equally to re-balance the long-tailed distribution. However, considering that some challenging classes may present diverse intra-class distributions, re-balancing all classes equally may lead to a significant performance drop. To address this, in this paper, we propose a curriculum learning-based framework called Flexible Sampling for the long-tailed skin lesion classification task. Specifically, we initially sample a subset of training data as anchor points based on the individual class prototypes. Then, these anchor points are used to pre-train an inference model to evaluate the per-class learning difficulty. Finally, we use a curriculum sampling module to dynamically query new samples from the rest training samples with the learning difficulty-aware sampling probability. We evaluated our model against several state-of-the-art methods on the ISIC dataset. The results with two long-tailed settings have demonstrated the superiority of our proposed training strategy, which achieves a new benchmark for long-tailed skin lesion classification.

Keywords

Cite

@article{arxiv.2204.03161,
  title  = {Flexible Sampling for Long-tailed Skin Lesion Classification},
  author = {Lie Ju and Yicheng Wu and Lin Wang and Zhen Yu and Xin Zhao and Xin Wang and Paul Bonnington and Zongyuan Ge},
  journal= {arXiv preprint arXiv:2204.03161},
  year   = {2025}
}
R2 v1 2026-06-24T10:40:36.834Z