Research map / Label-efficient and robust learning / Recognition and long-tail
Discriminatively Learned Convex Models for Set Based Face Recognition
Hakan Cevikalp, Golara Ghorban Dordinejad
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 |
|---|---|---|---|
| replace generatively learned affine hull with discriminatively learned affine hull (ablation) | AHISD · PaSC Control | verification rate (%): 80.97 -> 88.76 | Improved |
| replace generatively learned affine hull with discriminatively learned affine hull (ablation) | AHISD · PaSC Handheld | verification rate (%): 65.14 -> 77.39 | Improved |
| replace generatively learned convex hull with discriminatively learned convex hull (ablation) | CHISD · PaSC Control | verification rate (%): 88.48 -> 93.31 | Improved |
| replace generatively learned convex hull with discriminatively learned convex hull (ablation) | CHISD · PaSC Handheld | verification rate (%): 74.01 -> 85.00 | Improved |
| replace generatively learned affine hull with discriminatively learned affine hull (ablation) | AHISD · YouTube Celebrities (LBP) | accuracy (%): 62.0 -> 71.5 | Improved |
| replace generatively learned convex hull with discriminatively learned convex hull (ablation) | CHISD · YouTube Celebrities (LBP) | accuracy (%): 65.7 -> 71.2 | Improved |
| replace generatively learned affine hull with discriminatively learned affine hull (ablation) | AHISD · ESOGU-285 (LBP features) | accuracy (%): 66.8 -> 86.6 | Improved |
| replace generatively learned convex hull with discriminatively learned convex hull (ablation) | CHISD · ESOGU-285 (LBP features) | accuracy (%): 76.6 -> 89.0 | Improved |
| replace generatively learned affine hull with discriminatively learned affine hull (ablation) | AHISD · ESOGU-285 (CNN features) | accuracy (%): 81.32 -> 85.26 | Improved |
| replace generatively learned convex hull with discriminatively learned convex hull (ablation) | CHISD · ESOGU-285 (CNN features) | accuracy (%): 79.82 -> 85.70 | Improved |
| replace generatively learned affine hull with discriminatively learned affine hull (ablation) | AHISD · COX video-to-video (LBP) | accuracy (%): 44.3 -> 55.9 | Improved |
| replace generatively learned convex hull with discriminatively learned convex hull (ablation) | CHISD · COX video-to-video (LBP) | accuracy (%): 44.8 -> 75.1 | Improved |
Closest papers by meaning
- FaceCoresetNet: Differentiable Coresets for Face Set Recognition (AAAI 2024 · similarity 0.89)
- Deep Discriminative Feature Models (DDFMs) for Set Based Face Recognition and Distance Metric Learning (TPAMI 2022 · similarity 0.89)
- Video Based Face Recognition by Using Discriminatively Learned Convex Models (IJCV 2020 · similarity 0.88)
- Discriminative Covariance Oriented Representation Learning for Face Recognition With Image Sets (CVPR 2017 · similarity 0.88)
- Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors (ICLR 2025 · similarity 0.84)
- HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere (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.
