Research map / Label-efficient and robust learning / Recognition and long-tail
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
Yandong Guo, Lei Zhang, Yuxiao Hu, Xiaodong He, Jianfeng Gao
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 |
|---|---|---|---|
| use Random-set image instead of Hard-set image per celebrity | baseline CNN · MS-Celeb-1M measurement set (500 celebrities) | coverage at precision 95%: 0.442 -> 0.728 | Improved |
| raise required precision from 95% to 99% | baseline CNN · MS-Celeb-1M Hard set | coverage: 0.442 -> 0.052 | Hurt |
| raise required precision from 95% to 99% | baseline CNN · MS-Celeb-1M Random set | coverage: 0.728 -> 0.606 | Hurt |
| sample measurement celebrities with weight f^(1/sqrt(5)) instead of f (ablation) | measurement set construction · MS-Celeb-1M celebrity list | share of tail celebrities in measurement set: less than 10% -> about 25% | Improved |
| pre-train a small model on 500 celebrities before the 100K-class model (ablation) | baseline CNN · MS-Celeb-1M training | training convergence | Improved |
| initialize the small model from a pre-trained model (ablation) | baseline CNN · MS-Celeb-1M training | convergence speed | Improved |
Closest papers by meaning
- CelebV-HQ: A Large-Scale Video Facial Attributes Dataset (ECCV 2022 · similarity 0.88)
- The MegaFace Benchmark: 1 Million Faces for Recognition at Scale (CVPR 2016 · similarity 0.88)
- WebFace260M: A Benchmark for Million-Scale Deep Face Recognition (TPAMI 2022 · similarity 0.87)
- WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition (CVPR 2021 · similarity 0.86)
- Level Playing Field for Million Scale Face Recognition (CVPR 2017 · similarity 0.85)
- The Devil of Face Recognition is in the Noise (ECCV 2018 · similarity 0.85)
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.
