Research map / Label-efficient and robust learning / Recognition and long-tail
Disentangled Variational Representation for Heterogeneous Face Recognition
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the disentangled variational representation part (ablation) | LightCNN backbones · Oulu-CASIA NIR-VIS | VR@FAR=0.1%: 43.8 -> 50.7; 68.3 -> 79.8 | Helped |
| Add mean discrepancy minimization (ablation) | DVR with LightCNN-9 · CASIA NIR-VIS 2.0, Oulu-CASIA NIR-VIS, and BUAA-VisNir | VR@FAR=0.1%: 97.3 -> 98.1; 50.7 -> 61.3; 88.3 -> 91.0 | Helped |
| Add correlation alignment (ablation) | DVR with LightCNN-9 and LightCNN-29 · CASIA NIR-VIS 2.0, Oulu-CASIA NIR-VIS, and BUAA-VisNir | VR@FAR=0.1%: 61.3 -> 65.8; 83.0 -> 84.9 | Helped |
| Use LightCNN-29 instead of LightCNN-9 as the backbone | DVR · CASIA NIR-VIS 2.0, Oulu-CASIA NIR-VIS, and BUAA-VisNir | Rank-1 accuracy: 99.1 -> 99.7; 99.3 -> 100.0; 97.9 -> 99.2 | Helped |
Closest papers by meaning
- Learning Invariant Deep Representation for NIR-VIS Face Recognition (AAAI 2017 · similarity 0.90)
- Physically-Based Face Rendering for NIR-VIS Face Recognition (NeurIPS 2022 · similarity 0.89)
- Coupled Deep Learning for Heterogeneous Face Recognition (AAAI 2018 · similarity 0.88)
- Dual Variational Generation for Low Shot Heterogeneous Face Recognition (NeurIPS 2019 · similarity 0.87)
- Not Afraid of the Dark: NIR-VIS Face Recognition via Cross-Spectral Hallucination and Low-Rank Embedding (CVPR 2017 · similarity 0.86)
- TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification (AAAI 2025 · similarity 0.85)
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.