AI Paper Atlas

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

Learning To Learn Across Diverse Data Biases in Deep Face Recognition

Chang Liu, Xiang Yu, Yi-Hsuan Tsai, Masoud Faraki, Ramin Moslemi, Manmohan Chandraker, Yun Fu

CVPR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 23 citations (OpenAlex)

Check 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 occlusion-aware margin weighting (ablation)CosFace · OC-LFWaccuracy: 94.41 -> 94.52Improved
Add all modeled variation factors (ablation)CosFace · OC-LFWaccuracy: 94.41 -> 94.83Improved
Add head-pose-aware margin weighting (ablation)CosFace · CFP-FPaccuracy: 98.16 -> 98.35Improved
Add all modeled variation factors (ablation)CosFace · CFP-FPaccuracy: 98.16 -> 98.41Improved
Add all modeled variation factors (ablation)CosFace · RFW averageaccuracy: 97.94 -> 98.32Improved
Add all modeled variation factors (ablation)CosFace · RFWbias: 0.67 -> 0.51Improved
Add blur-aware margin weighting (ablation)CosFace · IJB-A (Vrf), FAR@0.001%verification rate: 93.22 -> 95.58Improved
Combine ethnicity and pose variation margins (ablation)CosFace · IJB-A (Vrf), FAR@0.01%verification rate: 97.13 -> 97.20No clear effect
Add blur variation margin to ethnicity and pose (ablation)CosFace · IJB-A (Vrf), FAR@0.01%verification rate: 97.20 -> 97.45Improved
Add all modeled variation factors (ablation)CosFace · IJB-A (Vrf), FAR@0.01%verification rate: 97.13 -> 97.46Improved
Replace CosFace with MvCoM-CosFaceCosFace · LFWaccuracy: 99.73 -> 99.80No clear effect
Replace CosFace with MvCoM-CosFaceCosFace · MegaFace1 uncleaned, Rank1Rank1: 80.03 -> 81.30Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 4 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