AI Paper Atlas

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

Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces

Jiankang Deng, Jia Guo, Tongliang Liu, Mingming Gong, Stefanos Zafeiriou

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 261 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
replace the single class center with K=3 sub-centers (ablation)ArcFace trained on MS1MV0 · IJB-C (MS1MV0, ResNet-50)TAR@FAR=1e-4: 90.27 -> 93.72Improved
increase sub-centers from K=3 to K=10 (ablation)sub-center ArcFace on MS1MV0 · IJB-C (MS1MV0, ResNet-50)TAR@FAR=1e-4: 93.72 -> 67.94Hurt
use max pooling instead of softmax pooling over sub-centers (ablation)sub-center ArcFace K=3 · IJB-C (MS1MV0, ResNet-50)TAR@FAR=1e-4: 93.55 -> 93.72Improved
drop non-dominant sub-centers and noisy samples beyond 75 degrees (ablation)sub-center ArcFace K=3 on MS1MV0 · IJB-C (MS1MV0, ResNet-50)TAR@FAR=1e-4: 93.72 -> 95.92Improved
drop non-dominant sub-centers and noisy samples instead of adding a compactness regularizer (ablation)sub-center ArcFace K=3 · IJB-C (MS1MV0, ResNet-50)TAR@FAR=1e-4: 93.64 -> 95.92Improved
vary drop threshold from 70 to 80 degrees (ablation)sub-center ArcFace K=3 drop 1 · IJB-C (MS1MV0, ResNet-50)TAR@FAR=1e-4: 95.91 / 95.92 / 95.74No clear effect
use sub-center ArcFace with drop instead of Co-miningMS1MV0 noisy training · IJB-C (MS1MV0, ResNet-50)TAR@FAR=1e-4: 93.82 -> 95.92Improved
use sub-centers on clean MS1MV3ArcFace · IJB-C (MS1MV3, ResNet-50)TAR@FAR=1e-4: 96.50 -> 96.43No clear effect
add sub-centers with drop under 25% synthetic open-set noiseArcFace · IJB-C (MS1MV3 open-set noise, ResNet-50)TAR@FAR=1e-4: 94.52 -> 95.89Improved
add sub-centers (K=3, no drop) under 25% synthetic close-set noiseArcFace · IJB-C (MS1MV3 close-set noise, ResNet-50)TAR@FAR=1e-4: 94.28 -> 93.57Hurt
add dropping to sub-centers under 50% close-set noise (ablation)sub-center ArcFace K=3 · IJB-C (MS1MV3 close-set noise, ResNet-50)TAR@FAR=1e-4: 72.04 -> 78.12Improved
train on larger Celeb500K with sub-center drop instead of MS1MV3 ArcFaceResNet-100 · IJB-C (ResNet-100)TAR@FAR=1e-4: 96.61 -> 96.96Improved

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