AI Paper Atlas

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

MixFairFace: Towards Ultimate Fairness via MixFair Adapter in Face Recognition

Fu-En Wang, Chien-Yi Wang, Min Sun, Shang-Hong Lai

AAAI 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 7 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
Balance estimated identity-bias differences with MixFair Adapter and inject them into the CosFace lossFace recognition trained on Balancedface · RFWiFPR-std (1e-5): 2.76 -> 2.05Improved
Balance estimated identity-bias differences with MixFair Adapter and inject them into the CosFace lossFace recognition trained on Globalface · RFWiFPR-std (1e-5): 2.64 -> 2.09Improved
Balance estimated identity-bias differences with MixFair Adapter and inject them into the CosFace lossFace recognition trained on MS1M · IJB-CiFPR-std (1e-5): 3.68 -> 2.53Improved
Use image-space mixup with soft labels instead of MixFairFaceFace recognition trained on Balancedface · RFWiFPR-std (1e-5): 2.76 -> 3.27Hurt
Use manifold mixup with soft labels instead of MixFairFaceFace recognition trained on Balancedface · RFWiFPR-std (1e-5): 2.76 -> 2.73No clear effect
Use image-space mixup with soft labels instead of MixFairFaceFace recognition trained on Globalface · RFWiFPR-std (1e-5): 2.64 -> 3.33Hurt
Use manifold mixup with soft labels instead of MixFairFaceFace recognition trained on Globalface · RFWiFPR-std (1e-5): 2.64 -> 2.49No clear effect
Use MixFairFace rather than CosFaceFace recognition trained on MS1M · IJB-CaTPR average (1e-2): 71.9 -> 69.5Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 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