AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology

Siyuan Yan, Ming Hu, Yiwen Jiang, Xieji Li, Hao Fei, Philipp Tschandl, Harald Kittler, Zongyuan Ge

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 42 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
train CLIP-style model on Derm1M (DermLIP ViT-B16/GPT77) vs BiomedCLIPDermLIP · Zero-shot classification averageaccuracy: .4408 -> .5607Improved
use PanDerm-B vision and PubMedBert text encoders instead of ViT-B16/GPT77 (ablation)DermLIP · Zero-shot classification averageaccuracy: .5607 -> .5879Improved
use PanDerm-B/PMB256 instead of ViT-B16/GPT77 (ablation)DermLIP · Zero-shot Fitzpatrick17Kaccuracy: .2278 -> .3162Improved
use PanDerm-B/PMB256 instead of ViT-B16/GPT77 (ablation)DermLIP · Zero-shot HAM10000accuracy: .6820 -> .6274Hurt
use longer text context (PMB256) with generic ViT-B16 instead of GPT77 (ablation)DermLIP · Zero-shot classification averageaccuracy: .5607 -> .5558Mixed
use PanDerm-B/PMB256 instead of ViT-B16/GPT77 (ablation)DermLIP · Linear eval average, 1% labelsaccuracy: .570 -> .586Improved
use PanDerm-B/PMB256 instead of ViT-B16/GPT77 (ablation)DermLIP · Linear eval average, 10% labelsaccuracy: .691 -> .696Improved
pretrain on Derm1M vs MONETDermLIP PanDerm-B/PMB256 · Linear eval average, 1% labelsaccuracy: .530 -> .586Improved
use PanDerm-B/PMB256 instead of ViT-B16/GPT77 (ablation)DermLIP · Retrieval Derm1M holdout I2TRecall@10: .4069 -> .5998Improved
use PanDerm-B/PMB256 instead of ViT-B16/GPT77 (ablation)DermLIP · Retrieval SkinCAP I2TRecall@10: .1567 -> .2018Improved
DermLIP vs MONET on concept identificationDermLIP ViT-B16/GPT77 · Derm7ptAUROC: 68.8% vs. 68.9%No clear effect
DermLIP vs MONET on concept identificationDermLIP ViT-B16/GPT77 · SkinCon + Derm7ptAUROC: 73.1%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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