AI Paper Atlas

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

Invariant Feature Regularization for Fair Face Recognition

Jiali Ma, Zhongqi Yue, Kagaya Tomoyuki, Suzuki Tomoki, Karlekar Jayashree, Sugiri Pranata, Hanwang Zhang

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 11 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 Inv-Reg to ArcfaceArcface ResNet-100 · MFRaverage accuracy (%): 76.90 -> 79.44Improved
add Inv-Reg to CIFPCIFP ResNet-100 · MFRaverage accuracy (%): 80.32 -> 81.17Improved
add Inv-Reg to ArcfaceArcface ResNet-50 · MFRAfrican accuracy (%): 74.54 -> 77.00Improved
add Inv-Reg to ArcfaceArcface ResNet-100 · DigiFace-1Mverification accuracy FPR=1e-4 (%): 64.32 -> 67.57Improved
add Inv-Reg to ArcfaceArcface ResNet-100 · IJB-Cverification accuracy (%): 95.60 -> 96.46Improved
use learned partitions instead of ground-truth race and gender partitions (ablation)Inv-Reg · MFR (ResNet-50)average accuracy (%): 74.84 -> 75.03Improved
use ground-truth partitions instead of no invariance (Arcface baseline) (ablation)Inv-Reg · MFR (ResNet-50)average accuracy (%): 73.43 -> 74.84Improved
increase number of subsets K from 2 to 4 (ablation)Inv-Reg · MFR (ResNet-50)average accuracy (%): 77.19 -> 76.94Hurt
increase discovered partitions from 1 to 3 (ablation)Inv-Reg · MFR (ResNet-50)average accuracy (%): 76.75 -> 77.19Improved
increase discovered partitions from 3 to 4 (ablation)Inv-Reg · MFR (ResNet-50)average accuracy (%): 77.19 -> 76.82Hurt
vary invariant penalty weight lambda between 0.02 and 0.2 (ablation)Inv-Reg · MFR (ResNet-50)accuracyNo clear effect

Earlier methods this paper compares with

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