AI Paper Atlas

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

Mitigating Gender Bias in Face Recognition using the von Mises-Fisher Mixture Model

Jean-Rémy Conti, Nathan Noiry, Stephan Clemencon, Vincent Despiegel, Stéphane Gentric

ICML 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 4 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 Ethical Module (EM-C, kappa0=45, kappa1=30) on top of frozen ArcFaceArcFace ResNet50 · LFW, FAR 10-4BFAR and BFRR jointly: BFAR 4.72→2.44, BFRR 10.27→9.18Improved
Add Ethical Module (EM-FAR, kappa0=15, kappa1=20)ArcFace ResNet50 · LFW, FAR 10-4BFAR: 4.72→2.11Improved
Add Ethical Module (EM-FRR, kappa0=25, kappa1=20)ArcFace ResNet50 · LFW, FAR 10-4BFAR: 4.72→33.65Hurt
Add Ethical Module (EM-FRR) to ArcFaceArcFace ResNet50 · LFW, FAR 10-4BFRR: 10.27→5.89Improved
Ethical Module (EM-FAR/EM-C) on CosFace/AdaCos/CurricularFace (MobileFaceNet)AdaCos, CosFace, CurricularFace · LFW, FAR 10-4BFAR: e.g., CosFace 2.51→1.13 (EM-FAR), AdaCos 3.84→1.41Improved
Ethical Module with gender-dependent concentration (kappa per gender) trained on frozen embeddingsArcFace ResNet50 vs PASS-G baseline · LFW, FAR 10-3BFAR: EM-C 1.20 vs PASS-G 2.11 vs original 1.81Improved
Ethical Module increases FRR@FAR error rate in some variantsArcFace ResNet50 and MobileFaceNet models · LFW, FAR 10-4FRR@FAR: e.g., ArcFace 0.078→0.151 (EM-FAR); CosFace 1.73→3.69 (EM-FAR)Hurt
Adversarial post-processing PASS-G baselineArcFace ResNet50 · LFW, FAR 10-4FRR@FAR: 0.078→0.315Hurt
Sweeping gender-specific concentration parameters (kappa0, kappa1) shows BFAR and BFRR trade off against each other (ablation)ArcFace ResNet50 Ethical Module · IJB-C grid search, FAR 10-3BFAR vs BFRRMixed

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