Contrastive Adapter Training and Consensus Knowledge Distillation for Multi-Source-Free Domain Adaptation in Skin Cancer Diagnosis

Paper recorded by Signals 4 on 2026-11-02 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-11-02 on arXiv · recorded by Signals 4 on 2026-11-03

Category: cs.AI · 人工智能 · first seen 2026-11-03

Abstract

Skin cancer diagnosis, particularly differentiating melanoma from benign nevi, is challenging due to the visual similarity between lesions. Although convolutional neural networks (CNNs) and vision transformers (ViTs) have shown promising performance, their effectiveness often deteriorates on data from heterogeneous clinical sources. Conventional domain adaptation methods address domain shift but r

Read on arXiv →