Research map / Label-efficient and robust learning / Domain adaptation and generalization
Cross-Domain Similarity Learning for Face Recognition in Unseen Domains
Check 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 Cross-Domain Triplet loss and meta-learning pipeline | Face recognition model · CEF Caucasian unseen | TAR@FAR 0.001: 64.31 -> 65.74 | Helped |
| Add Cross-Domain Triplet loss and meta-learning pipeline | Face recognition model · CEF African-American unseen | TAR@FAR 0.001: 90.66 -> 94.89 | Helped |
| Add Cross-Domain Triplet loss and meta-learning pipeline | Face recognition model · CEF Asian unseen | TAR@FAR 0.001: 85.54 -> 88.74 | Helped |
| Add Cross-Domain Triplet loss and meta-learning pipeline | Face recognition model · CEF Indian unseen | TAR@FAR 0.001: 84.17 -> 87.84 | Helped |
| Add Cross-Domain Triplet loss and meta-learning pipeline | Face recognition model · RFW Caucasian unseen | TAR@FAR 0.001: 63.81 -> 65.20 | Helped |
| Add Cross-Domain Triplet loss and meta-learning pipeline | Face recognition model · RFW African unseen | TAR@FAR 0.001: 75.31 -> 77.90 | Helped |
| Add Cross-Domain Triplet loss and meta-learning pipeline | Face recognition model · RFW Asian unseen | TAR@FAR 0.001: 69.02 -> 69.17 | Helped |
| Add Cross-Domain Triplet loss and meta-learning pipeline | Face recognition model · RFW Indian unseen | TAR@FAR 0.001: 71.44 -> 76.63 | Helped |
| Add Cross-Domain Triplet loss and meta-learning pipeline | Face recognition model · CACD-VS | AUC: 99.8 -> 99.8 | No clear effect |
| Add Cross-Domain Triplet loss and meta-learning pipeline | Face recognition model · CASIA NIR-VIS 2.0 | TAR@FAR 0.001: 72.33 -> 76.41 | Helped |
| Add Cross-Domain Triplet loss and meta-learning pipeline | Face recognition model · Multi-PIE cross pose | TAR@FAR 0.001: 74.54 -> 76.62 | Helped |
| Add identity classification loss (ablation) | Full proposed method · RFW Caucasian unseen | TAR@FAR 0.001: 64.24 -> 65.20 | Helped |
Closest papers by meaning
- Unsupervised Domain Adaptation for Distance Metric Learning (ICLR 2019 · similarity 0.87)
- Learning Meta Face Recognition in Unseen Domains (CVPR 2020 · similarity 0.87)
- Cross-Domain Face Presentation Attack Detection via Multi-Domain Disentangled Representation Learning (CVPR 2020 · similarity 0.86)
- Link-based Contrastive Learning for One-Shot Unsupervised Domain Adaptation (CVPR 2025 · similarity 0.86)
- UMFN: Unified Multi-Domain Face Normalization for Joint Cross-domain Prototype Learning and Heterogeneous Face Recognition (CVPR 2025 · similarity 0.85)
- QCS:Feature Refining from Quadruplet Cross Similarity for Facial Expression Recognition (AAAI 2025 · similarity 0.84)
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.