Research map / Label-efficient and robust learning / Recognition and long-tail
Discriminative Covariance Oriented Representation Learning for Face Recognition With Image Sets
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 |
|---|---|---|---|
| Learn image representations with the Graph Embedding scheme instead of FN features | Covariance-based face-set classification · YTC | accuracy: 85.21 ±1.57 -> 91.03±1.22 | Helped |
| Learn image representations with the Softmax Regression scheme instead of FN features | Covariance-based face-set classification · YTC | accuracy: 85.21 ±1.57 -> 94.85±0.96 | Helped |
| Learn image representations with the Graph Embedding scheme instead of FN features | Covariance-based face-set classification · YTF | accuracy: 79.07 -> 81.34 | Helped |
| Learn image representations with the Softmax Regression scheme instead of FN features | Covariance-based face-set classification · YTF | accuracy: 79.07 -> 82.25 | Helped |
| Learn image representations with the Graph Embedding scheme instead of FN features | Covariance-based face-set classification · PaSC control videos | verification rate at FAR 0.01: 52.31 -> 55.65 | Helped |
| Learn image representations with the Softmax Regression scheme instead of FN features | Covariance-based face-set classification · PaSC handheld videos | verification rate at FAR 0.01: 50.15 -> 55.73 | Helped |
| Use Softmax Regression rather than Graph Embedding for representation learning | DCRL · YTC | accuracy: 91.03±1.22 -> 94.85±0.96 | Helped |
| Use Softmax Regression rather than Graph Embedding for representation learning | DCRL · YTF | accuracy: 81.34 -> 82.25 | Helped |
| Use Softmax Regression rather than Graph Embedding for representation learning | DCRL · PaSC handheld videos | verification rate at FAR 0.01: 53.06 -> 55.73 | Helped |
| Replace FN image features with learned GE features (ablation) | Face-set classification with LEM · PaSC control videos | performance: 33.63 -> 35.74 | Helped |
| Replace FN image features with learned GE features (ablation) | Face-set classification with CDL · PaSC control videos | performance: 52.31 -> 55.65 | Helped |
| Replace FN image features with learned SR features (ablation) | Face-set classification with CDL · PaSC control videos | performance: 52.31 -> 56.43 | Helped |
Closest papers by meaning
- FaceCoresetNet: Differentiable Coresets for Face Set Recognition (AAAI 2024 · similarity 0.87)
- Mis-Classified Vector Guided Softmax Loss for Face Recognition (AAAI 2020 · similarity 0.86)
- CosFace: Large Margin Cosine Loss for Deep Face Recognition (CVPR 2018 · similarity 0.86)
- Attributes Shape the Embedding Space of Face Recognition Models (ICML 2025 · similarity 0.85)
- Masked Face Recognition with Generative-to-Discriminative Representations (ICML 2024 · similarity 0.84)
- 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.