AI Paper Atlas

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

Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition

Ran He, Xiang Wu, Zhenan Sun, Tieniu Tan

TPAMI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 318 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 low-rank constraint (ablation)WCNN · CASIA NIR-VIS 2.0Rank-1 accuracy: 98.4 -> 98.7Improved
add low-rank constraint (ablation)WCNN · CASIA NIR-VIS 2.0VR@FAR=0.1%: 97.6 -> 98.4Improved
add low-rank constraint (ablation)WCNN · Oulu-CASIA NIR-VISRank-1 accuracy: 96.4 -> 98.0Improved
add low-rank constraint (ablation)WCNN · Oulu-CASIA NIR-VISVR@FAR=0.1%: 50.9 -> 54.6Improved
add low-rank constraint (ablation)WCNN · BUAA VisNirRank-1 accuracy: 95.4 -> 97.4Improved
add low-rank constraint (ablation)WCNN · BUAA VisNirVR@FAR=0.1%: 86.9 -> 91.9Improved
add low-rank constraint (ablation)IDR · Oulu-CASIA NIR-VISVR@FAR=0.1%: 46.2 -> 50.3Improved
add low-rank constraint (ablation)IDR · BUAA VisNirVR@FAR=0.1%: 84.7 -> 86.0Improved
replace IDR with WCNN (Wasserstein distance based invariant feature learning)IDR · CASIA NIR-VIS 2.0VR@FAR=0.1%: 95.7 -> 97.6Improved
replace IDR with WCNNIDR · Oulu-CASIA NIR-VISRank-1 accuracy: 94.3 -> 96.4Improved
replace IDR with WCNNIDR · BUAA VisNirVR@FAR=0.1%: 84.7 -> 86.9Improved
train on NIR-VIS data instead of using VIS-only deep modelsVGG · CASIA NIR-VIS 2.0Rank-1 accuracy: 62.1 -> 98.7Improved

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