Flexible Sampling for Long-tailed Skin Lesion Classification

TL;DR

This paper introduces a curriculum learning-based flexible sampling framework to improve long-tailed skin lesion classification, addressing intra-class diversity and challenging class distribution issues.

Contribution

It proposes a novel dynamic sampling method that adapts to class difficulty, outperforming existing methods on the ISIC dataset for long-tailed skin lesion classification.

Findings

Achieves new state-of-the-art results on ISIC dataset

Demonstrates effectiveness in handling intra-class diversity

Outperforms several existing long-tailed learning methods

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.