AI Paper Atlas

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

Domain Balancing: Face Recognition on Long-Tailed Domains

Dong Cao, Xiangyu Zhu, Xingyu Huang, Jianzhu Guo, Zhen Lei

CVPR 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 78 citations (OpenAlex)

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
Apply Domain BalancingResNet50 trained on MS1MV2 · LFWverification accuracy (%): 99.62% to 99.78%Improved
Apply Domain BalancingResNet50 · LFW BLUFR, VR@FAR=0.01%verification rate: 99.23 to 99.53Improved
Apply Domain BalancingResNet50 · CALFWverification accuracy (%): 95.45 to 96.08Improved
Apply Domain BalancingResNet50 · CPLFWverification accuracy (%): 92.08 to 92.63Improved
Apply Domain BalancingResNet50 · AgeDBverification accuracy (%): 97.83 to 97.90Improved
Apply Domain BalancingResNet50 · MegaFace Challenge1Rank-1 identification accuracy (%): 95.53 to 96.35Improved
Add DBM to RBM (ablation)ResNet18 trained on CASIA-Webface · Average of LFW, CALFW, CPLFW and AgeDBaverage accuracy (%): 92.12 to 92.88Improved
Add a soft gate to the residual enhancement (ablation)RBM · Average of LFW, CALFW, CPLFW and AgeDBaverage accuracy (%): 91.25 to 92.12Improved
Add RBM with its soft gate (ablation)Baseline face recognition model · Average of LFW, CALFW, CPLFW and AgeDBaverage accuracy (%): 91.35 to 92.12Improved
Set DFI nearest-neighbor K to 0 (ablation)Domain Balancing · LFWverification accuracy (%): 99.3 to 98.8Hurt
Set DFI nearest-neighbor K to 1,000 instead of 100 (ablation)Domain Balancing · LFWverification accuracy (%): 99.3 to 99.1Hurt
Set DFI nearest-neighbor K to 3,000 instead of 100 (ablation)Domain Balancing · LFWverification accuracy (%): 99.3 to 99.2Hurt

Earlier methods this paper compares with

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