Research map / Label-efficient and robust learning / Recognition and long-tail
More Information Supervised Probabilistic Deep Face Embedding Learning
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 proposed linear margin function instead of other margin softmax losses (ablation) | LinearFace · LFW | verification accuracy: 99.55 | Helped |
| add the proposed linear margin function instead of other margin softmax losses (ablation) | LinearFace · CFP-FP | verification accuracy: 97.01 | Helped |
| add teacher-student learning (ablation) | LinearFace · CALFW | verification accuracy: 93.3 -> 93.73 | Helped |
| add teacher-student learning (ablation) | LinearFace · CPLFW | verification accuracy: 89.08 -> 89.75 | Helped |
| add teacher-student learning (ablation) | LinearFace · AgeDB-30 | verification accuracy: 94.66 -> 95.05 | Helped |
| add the generative decode part (ablation) | LinearFace · CALFW | verification accuracy: 93.3 -> 94.3 | Helped |
| add the generative decode part (ablation) | LinearFace · CPLFW | verification accuracy: 89.08 -> 90.13 | Helped |
| add the generative decode part (ablation) | LinearFace · AgeDB-30 | verification accuracy: 94.66 -> 95.91 | Helped |
| combine teacher-student learning and the generative decode part (ablation) | LinearFace · CALFW | verification accuracy: 93.3 -> 94.58 | Helped |
| combine teacher-student learning and the generative decode part (ablation) | LinearFace · CPLFW | verification accuracy: 89.08 -> 90.33 | Helped |
| combine teacher-student learning and the generative decode part (ablation) | LinearFace · AgeDB-30 | verification accuracy: 94.66 -> 95.91 | Helped |
| use LATSE rather than ArcFace | face verification · CALFW | verification accuracy: 95.45 -> 96.20 | Helped |
Closest papers by meaning
- Mis-Classified Vector Guided Softmax Loss for Face Recognition (AAAI 2020 · similarity 0.88)
- CosFace: Large Margin Cosine Loss for Deep Face Recognition (CVPR 2018 · similarity 0.88)
- Killing Two Birds With One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC (CVPR 2022 · similarity 0.87)
- Softmax Dissection: Towards Understanding Intra- and Inter-Class Objective for Embedding Learning (AAAI 2020 · similarity 0.87)
- Loss Function Search for Face Recognition (ICML 2020 · similarity 0.87)
- Learning Towards The Largest Margins (ICLR 2022 · similarity 0.87)
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.