AI Paper Atlas

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

LAMP-HQ: A Large-Scale Multi-pose High-Quality Database and Benchmark for NIR-VIS Face Recognition

Aijing Yu, Haoxue Wu, Huaibo Huang, Zhen Lei, Ran He

IJCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 48 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 content loss (ablation)VSANet · LAMP-HQ (LightCNN-29)Rank-1 accuracy (%): 63.49 -> 97.46Improved
add style loss (ablation)VSANet · LAMP-HQ (LightCNN-29)Rank-1 accuracy (%): 94.35 -> 97.46Improved
add identity-preserving loss (ablation)VSANet · LAMP-HQ (LightCNN-29)Rank-1 accuracy (%): 94.12 -> 97.46Improved
add adversarial loss (ablation)VSANet · LAMP-HQ (LightCNN-29)Rank-1 accuracy (%): 95.52 -> 97.46Improved
add AdaIN operation (ablation)VSANet · LAMP-HQ (LightCNN-29)Rank-1 accuracy (%): 96.70 -> 97.46Improved
add spectral conditional attention (SCA) (ablation)VSANet · LAMP-HQ (LightCNN-29)Rank-1 accuracy (%): 95.72 -> 97.46Improved
add spectral conditional attention (SCA) (ablation)VSANet · LAMP-HQ (LightCNN-9)Rank-1 accuracy (%): 92.74 -> 94.09Improved
add content loss (ablation)VSANet · LAMP-HQ (LightCNN-9)Rank-1 accuracy (%): 54.21 -> 94.09Improved
replace NIR probe with synthesized VIS imagesVSANet · LAMP-HQ (LightCNN-9)Rank-1 accuracy (%): 89.77 -> 94.09Improved
replace NIR probe with synthesized VIS imagesVSANet · LAMP-HQ (LightCNN-29)Rank-1 accuracy (%): 94.94 -> 97.46Improved
fine-tune LightCNN-29 on NIR-VIS training imagesLightCNN-29 · LAMP-HQRank-1 accuracy (%): 97.46 -> 94.23Hurt
fine-tune LightCNN-29 on synthesized VIS imagesLightCNN-29 · LAMP-HQRank-1 accuracy (%): 97.46 -> 95.81Hurt

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