Research map / Label-efficient and robust learning / Recognition and long-tail
Coupled Deep Learning 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 relevance constraints to the softmax objective (ablation) | Light CNN for heterogeneous face matching · CASIA NIR-VIS 2.0 | VR@FAR=0.1%: +0.91% | Helped |
| use cross-modal ranking alone instead of softmax (ablation) | Light CNN for heterogeneous face matching · CASIA NIR-VIS 2.0 | VR@FAR=0.1%: 93.66% vs 93.23% | Hurt |
| combine softmax, relevance constraints, and cross-modal ranking (ablation) | Light CNN for heterogeneous face matching · CASIA NIR-VIS 2.0 | VR@FAR=0.1%: 93.66 -> 98.32 | Helped |
| use cross-modal ranking alone instead of softmax (ablation) | Light CNN for heterogeneous face matching · CASIA NIR-VIS 2.0 | VR@FAR=0.01%: 80.76% vs 78.93% | Hurt |
| combine softmax, relevance constraints, and cross-modal ranking | Light CNN for heterogeneous face matching · CASIA NIR-VIS 2.0 | Rank-1 accuracy: 97.33% to 98.62% | Helped |
| use CDL rather than the strongest listed CNN baseline | Face matching · IIIT-D Sketch | Rank-1: 84.24 -> 85.35 | Helped |
Closest papers by meaning
- Disentangled Variational Representation for Heterogeneous Face Recognition (AAAI 2019 · similarity 0.88)
- Asymmetric Joint Learning for Heterogeneous Face Recognition (AAAI 2018 · similarity 0.88)
- UMFN: Unified Multi-Domain Face Normalization for Joint Cross-domain Prototype Learning and Heterogeneous Face Recognition (CVPR 2025 · similarity 0.84)
- UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognition (ICLR 2025 · similarity 0.83)
- HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere (ICLR 2025 · similarity 0.83)
- Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors (ICLR 2025 · 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.