AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

SkinCon: A skin disease dataset densely annotated by domain experts for fine-grained debugging and analysis

Roxana Daneshjou, Mert Yuksekgonul, Zhuo Ran Cai, Roberto A. Novoa, James Zou

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Prototype and concept dictionary models · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace original DeepDerm with PCBM using SkinCon conceptsDeepDerm · DDItest AUC: 0.595 -> 0.639Improved
Replace original DeepDerm with PCBM using SkinCon conceptsDeepDerm · DDI Fitzpatrick III-IVtest AUC: 0.632 -> 0.727Improved
Replace original DeepDerm with PCBM using SkinCon conceptsDeepDerm · DDI Fitzpatrick V-VItest AUC: 0.528 -> 0.542Improved
Replace original DeepDerm with PCBM using SkinCon conceptsDeepDerm · DDI Fitzpatrick I-IItest AUC: 0.649 -> 0.643No clear effect
Increase the number of training samples per concept for linear probes (ablation)CAV probes · SkinCon conceptsprobe accuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy