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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add content loss (ablation) | VSANet · LAMP-HQ (LightCNN-29) | Rank-1 accuracy (%): 63.49 -> 97.46 | Improved |
| add style loss (ablation) | VSANet · LAMP-HQ (LightCNN-29) | Rank-1 accuracy (%): 94.35 -> 97.46 | Improved |
| add identity-preserving loss (ablation) | VSANet · LAMP-HQ (LightCNN-29) | Rank-1 accuracy (%): 94.12 -> 97.46 | Improved |
| add adversarial loss (ablation) | VSANet · LAMP-HQ (LightCNN-29) | Rank-1 accuracy (%): 95.52 -> 97.46 | Improved |
| add AdaIN operation (ablation) | VSANet · LAMP-HQ (LightCNN-29) | Rank-1 accuracy (%): 96.70 -> 97.46 | Improved |
| add spectral conditional attention (SCA) (ablation) | VSANet · LAMP-HQ (LightCNN-29) | Rank-1 accuracy (%): 95.72 -> 97.46 | Improved |
| add spectral conditional attention (SCA) (ablation) | VSANet · LAMP-HQ (LightCNN-9) | Rank-1 accuracy (%): 92.74 -> 94.09 | Improved |
| add content loss (ablation) | VSANet · LAMP-HQ (LightCNN-9) | Rank-1 accuracy (%): 54.21 -> 94.09 | Improved |
| replace NIR probe with synthesized VIS images | VSANet · LAMP-HQ (LightCNN-9) | Rank-1 accuracy (%): 89.77 -> 94.09 | Improved |
| replace NIR probe with synthesized VIS images | VSANet · LAMP-HQ (LightCNN-29) | Rank-1 accuracy (%): 94.94 -> 97.46 | Improved |
| fine-tune LightCNN-29 on NIR-VIS training images | LightCNN-29 · LAMP-HQ | Rank-1 accuracy (%): 97.46 -> 94.23 | Hurt |
| fine-tune LightCNN-29 on synthesized VIS images | LightCNN-29 · LAMP-HQ | Rank-1 accuracy (%): 97.46 -> 95.81 | Hurt |
Closest papers by meaning
- Learning Invariant Deep Representation for NIR-VIS Face Recognition (AAAI 2017 · similarity 0.91)
- Adversarial Cross-Spectral Face Completion for NIR-VIS Face Recognition (TPAMI 2019 · similarity 0.91)
- Physically-Based Face Rendering for NIR-VIS Face Recognition (NeurIPS 2022 · similarity 0.90)
- Hypergraph-Guided Disentangled Spectrum Transformer Networks for Near-Infrared Facial Expression Recognition (AAAI 2024 · similarity 0.85)
- Multi-Energy Guided Image Translation with Stochastic Differential Equations for Near-Infrared Facial Expression Recognition (AAAI 2024 · similarity 0.84)
- EFHQ: Multi-purpose ExtremePose-Face-HQ dataset (CVPR 2024 · similarity 0.83)
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.
