Reproduce “Contrastive Adapter Training and Consensus Knowledge Distillation for Multi-Source-Free Domain Adaptation in Skin Cancer Diagnosis” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Ali Abedi, Q. M. Jonathan Wu, Ning Zhang, Farhad Pourpanah
The authors introduce CAT-CKD for binary melanoma-versus-nevus classification across five datasets. It first aligns same-class features from labeled sources using adapters in a frozen vision transformer, then trains a target-site student to match averaged predictions from source models on unlabeled images. CAT-CKD reports average AUROC of 86.1 ± 0.4, versus 84.3 ± 0.4 for Bi-ATEN, but trails it on PAD-UFES-20.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.