English

DerMAE: Improving skin lesion classification through conditioned latent diffusion and MAE distillation

Computer Vision and Pattern Recognition 2026-02-24 v1

Abstract

Skin lesion classification datasets often suffer from severe class imbalance, with malignant cases significantly underrepresented, leading to biased decision boundaries during deep learning training. We address this challenge using class-conditioned diffusion models to generate synthetic dermatological images, followed by self-supervised MAE pretraining to enable huge ViT models to learn robust, domain-relevant features. To support deployment in practical clinical settings, where lightweight models are required, we apply knowledge distillation to transfer these representations to a smaller ViT student suitable for mobile devices. Our results show that MAE pretraining on synthetic data, combined with distillation, improves classification performance while enabling efficient on-device inference for practical clinical use.

Keywords

Cite

@article{arxiv.2602.19848,
  title  = {DerMAE: Improving skin lesion classification through conditioned latent diffusion and MAE distillation},
  author = {Francisco Filho and Kelvin Cunha and Fábio Papais and Emanoel dos Santos and Rodrigo Mota and Thales Bezerra and Erico Medeiros and Paulo Borba and Tsang Ing Ren},
  journal= {arXiv preprint arXiv:2602.19848},
  year   = {2026}
}

Comments

4 pages, 2 figures, 1 table, isbi2026

R2 v1 2026-07-01T10:47:23.985Z