AI Paper Atlas

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

Do We Really Need to Collect Millions of Faces for Effective Face Recognition?

Iacopo Masi, Anh Tuấn Trần, Tal Hassner, Jatuporn Toy Leksut, Gérard Medioni

ECCV 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 352 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 pose augmentation to training data (ablation)VGGNet-19 on CASIA · IJB-A verification (with video pooling)TAR @ FAR=0.01: 75.0 -> 86.3Improved
add pose augmentation to training data (ablation)VGGNet-19 on CASIA · IJB-A identification (with video pooling)Rank-1: 77.8 -> 88.0Improved
add shape variation to pose augmentation (ablation)VGGNet-19 on CASIA · IJB-A verification (with video pooling)TAR @ FAR=0.01: 86.3 -> 87.8Improved
add expression (closed mouth) synthesis to pose and shape augmentation (ablation)VGGNet-19 on CASIA · IJB-A verification (with video pooling)TAR @ FAR=0.01: 87.8 -> 88.1Improved
add expression synthesis to pose and shape augmentation (ablation)VGGNet-19 on CASIA · IJB-A verification (without video pooling)TAR @ FAR=0.001: 62.0 -> 63.6Improved
add video pooling of features within each video (ablation)Full method · IJB-A verificationTAR @ FAR=0.001: 63.6 -> 71.0Improved
add video pooling of features within each video (ablation)Full method · IJB-A identificationRank-1: 87.2 -> 89.1Improved
replace mean fusion with SoftMax template fusion (ablation)Template score pooling · IJB-A verificationTAR @ FAR=0.01: 79.9 -> 86.6Improved
replace max fusion with SoftMax template fusion (ablation)Template score pooling · IJB-A verificationTAR @ FAR=0.001: 46.4 -> 63.6Improved
combine in-plane alignment with test-time pose synthesis (ablation)Full method · IJB-A verification (without video pooling)TAR @ FAR=0.01: 86.6 -> 87.8Improved
combine in-plane alignment with test-time pose synthesis (ablation)Full method · IJB-A identification (with video pooling)Rank-1: 89.1 -> 90.6Improved
use only rendered images instead of in-plane aligned images at test time (ablation)Full method · IJB-A verification (with video pooling)TAR @ FAR=0.01: 88.1 -> 84.8Hurt

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