AI Paper Atlas

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

Range Loss for Deep Face Recognition With Long-Tailed Training Data

Xiao Zhang, Zhiyuan Fang, Yandong Wen, Zhifeng Li, Yu Qiao

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 472 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 range loss to softmax, trained on full long-tailed set A-0VGG-Face · LFW (A-0)accuracy: 97.87% to 98.63%Improved
add range loss to softmax, trained on full long-tailed set A-0VGG-Face · YTF (A-0)accuracy: 92.0% to 93.50%Improved
keep the tailed data (A-2 to A-0) when training with range loss (ablation)Range loss + softmax · LFWaccuracy: accuracy increase by 0.18% in LFW and 0.3% in YTF from A-2 to A-0Improved
keep the tailed data (A-2 to A-0) when training with contrastive loss (ablation)Contrastive loss + softmax · LFWaccuracy: 98.47% to 98.35%Hurt
keep the tailed data (A-2 to A-0) when training with triplet loss (ablation)Triplet loss + softmax · LFWaccuracy: 98.40% to 98.10%Hurt
keep the tailed data (A-2 to A-0) when training with center loss (ablation)Center loss + softmax · LFWaccuracy: 98.57% to 98.22%Hurt
remove half of tailed data (A-0 to A-2) (ablation)Softmax VGG-Face · LFWaccuracy: 97.87% to 98.25%Improved
remove all tailed data (A-2 to A-4) (ablation)Softmax VGG-Face · LFWaccuracy: 98.25% to 95.97%Hurt
remove tail identities, 4000 to 1000 identities (B-0 to B-3) (ablation)Softmax AlexNet · LFWaccuracy: 78.73% to 83.77%Improved
use k=3 instead of k=2 largest ranges in intra-class loss (ablation)Range loss · LFWaccuracy: slightly improvement with 0.03% for LFW on average but much hard to trainMixed
add FaceNet hard mining to softmax baseline instead of range lossVGG on long-tailed data · LFWaccuracy: 96.55% in LFW versus 98.13% in LFWHurt
add range loss to ResNet trained on long-tailed dataResNet · BLUFR verification (FAR=0.1%)accuracy: 90.03% to 92.10%Improved

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