AI Paper Atlas

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

How to Boost Face Recognition with StyleGAN?

Artem Sevastopolskiy, Yury Malkov, Nikita Durasov, Luisa Verdoliva, Matthias Nießner

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 18 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
pretrain encoder into StyleGAN latent space on unlabeled African+Asian faces before face recognition fine-tuningArcFace R-50 · RB-WebFace TPR@FPR=1e-3 (African)TPR: 86.73 -> 91.51Improved
add StyleGAN pretrainingArcFace R-50 · RFW average accuracyaccuracy: 94.39 -> 95.09Improved
add StyleGAN pretraining to other FR methodsSphereFace · RB-WebFace TPR@FPR=1e-3 (African)TPR: 89.51 -> 90.52Improved
add StyleGAN pretrainingGAC · RB-WebFace TPR@FPR=1e-3 (African)TPR: 89.13 -> 90.80Improved
increase unlabeled prior dataset from 1% to 100% (ablation)StyleGAN pretraining · RB-WebFace TPR@FPR=1e-3 (African)TPR: 90.44 -> 91.51Improved
use StyleGAN-encoder pretraining instead of autoencoder pretraining (ablation)pretraining strategy · RB-WebFace TPR@FPR=1e-3 (African)TPR: 90.83 -> 91.51Improved
use StyleGAN-encoder pretraining instead of VAE pretraining (ablation)pretraining strategy · RB-WebFace TPR@FPR=1e-3 (African)TPR: 90.39 -> 91.51Improved
add synthetic StyleGAN interpolation samples instead of pretraining (ablation)ArcFace R-50 · RB-WebFace TPR@FPR=1e-3 (African)TPR: 86.73 -> 86.85 with 6M interpsNo clear effect
add pretraining on ResNet-100 backboneArcFace R-100 · RB-WebFace TPR@FPR=1e-3 (African)TPR: 91.55 -> 93.00Improved
reduce labeled face recognition data (ablation)StyleGAN pretraining · RFW and RB-WebFaceaccuracy/TPR gainImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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