English

An Evaluation of Self-Supervised Pre-Training for Skin-Lesion Analysis

Computer Vision and Pattern Recognition 2022-08-23 v3

Abstract

Self-supervised pre-training appears as an advantageous alternative to supervised pre-trained for transfer learning. By synthesizing annotations on pretext tasks, self-supervision allows to pre-train models on large amounts of pseudo-labels before fine-tuning them on the target task. In this work, we assess self-supervision for the diagnosis of skin lesions, comparing three self-supervised pipelines to a challenging supervised baseline, on five test datasets comprising in- and out-of-distribution samples. Our results show that self-supervision is competitive both in improving accuracies and in reducing the variability of outcomes. Self-supervision proves particularly useful for low training data scenarios (<1500<1\,500 and <150<150 samples), where its ability to stabilize the outcomes is essential to provide sound results.

Keywords

Cite

@article{arxiv.2106.09229,
  title  = {An Evaluation of Self-Supervised Pre-Training for Skin-Lesion Analysis},
  author = {Levy Chaves and Alceu Bissoto and Eduardo Valle and Sandra Avila},
  journal= {arXiv preprint arXiv:2106.09229},
  year   = {2022}
}

Comments

18 pages, 3 figures. Accepted at Seventh ISIC Skin Image Analysis Workshop @ECCV 2022