AI Paper Atlas

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

FairGen: Enhancing Fairness in Text-to-Image Diffusion Models via Self-Discovering Latent Directions

Yilei Jiang, Wei-Hong Li, Yiyuan Zhang, Minghong Cai, Xiangyu Yue

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Fairness and bias in generative models · 3 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
restrict adapters to cross-attention layers instead of all layers (ablation)FairGen · Intersectional debiasingFD: 0.165 -> 0.047Improved
restrict adapters to cross-attention layers instead of non-CA layers (ablation)FairGen · Intersectional debiasingFD: 0.158 -> 0.047Improved
restrict adapters to cross-attention layers instead of all layers (ablation)FairGen · Intersectional debiasingBRISQUE: 35.00 -> 39.50Improved
add orthogonal regularization (ablation)FairGen · Intersectional debiasingFD: 0.143 -> 0.047Improved
add orthogonal regularization (ablation)FairGen · Intersectional debiasingCLIPsim: 0.29 -> 0.36Improved
add orthogonal regularization (ablation)FairGen · Intersectional debiasingBRISQUE: 37.92 -> 39.50Improved
FairGen vs Original SDOriginal SD · Gender debiasing (0.5,0.5)FD: 0.424 -> 0.003Improved
FairGen vs Original SDOriginal SD · Gender debiasing (0.2,0.8)FD: 0.847 -> 0.005Improved
FairGen vs Original SDOriginal SD · Racial debiasing (0.25 each)FD: 0.384 -> 0.095Improved
FairGen vs Original SDOriginal SD · Racial debiasing (0.4,0.3,0.2,0.1)FD: 0.497 -> 0.150Improved
FairGen vs Original SDOriginal SD · Intersectional debiasingFD: 0.214 -> 0.047Improved
train adapters on SD v2.1, test on v1.4FairGen · Gender debiasing transferFD: 0.003 -> 0.006No clear effect

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