AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

BiasMitigateGan: SYNTHESIZING FAIR TRAINING DATA FOR DERMATOLOGY AI USING DIFFUSION MODELS

AbdulHuq Mohammed

IJCV 2025 · Image generation › Text-to-image diffusion · approach: Fairness and bias in generative models · 0 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
add fairness-aware conditional diffusion and resampling versus standard fine-tuned diffusionStable Diffusion · FST IV-VIFID: 32.7 -> 12.8Improved
add BiasMitigateGAN synthetic data to training instead of standard diffusion datamelanoma ResNet-50 classifier · FST IV-VIdiagnostic accuracy: 68% -> 92%Improved
add BiasMitigateGAN synthetic datamelanoma ResNet-50 classifier · FST IV-VIfairness gap: 27% -> 3%Improved
add BiasMitigateGAN synthetic datamelanoma ResNet-50 classifier · FST IV-VIEDFR: 0.21 -> 0.07Improved
add expert-judged realism from fairness trainingsynthetic images · FST IV-VIexpert realism score: 2.1/5.0 -> 4.3/5.0Improved
add fairness loss (ablation)BiasMitigateGAN · skin typesFID variance: 4x lower varianceImproved
add FST conditioning (ablation)BiasMitigateGAN · generated skin type distributionmode collapse: >90% of images FST II-IIIImproved
add fairness mechanismsBiasMitigateGAN · FST I-IIIdiagnostic accuracyNo clear effect

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