Research map / Label-efficient and robust learning / Recognition and long-tail
Level Playing Field for Million Scale Face Recognition
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 |
|---|---|---|---|
| train 3DiVi on MF2 instead of MF1 | 3DiVi · FaceScrub | Rank-1 identification rate: 33.705% -> 57.045% | Helped |
| train 3DiVi on MF2 instead of MF1 | 3DiVi · FG-Net | Rank-1 identification rate: 15.780% -> 35.790% | Helped |
| train SphereFace on MF2 instead of MF1 | SphereFace · FaceScrub | Rank-1 identification rate: 75.766% -> 58.933% | Hurt |
| train SphereFace on MF2 instead of MF1 | SphereFace · FG-Net | Rank-1 identification rate: 47.582% -> 38.208% | Hurt |
| train GRCCV on MF2 instead of MF1 | GRCCV · FaceScrub | Rank-1 identification rate: 77.147% -> 75.772% | Hurt |
| train GRCCV on MF2 instead of MF1 | GRCCV · FG-Net | Rank-1 identification rate: 24.783% -> 21.039% | Hurt |
| train algorithms on MF2 rather than allowing unrestricted training data | face recognition algorithms · FaceScrub | Rank-1 identification rate: 75.772% vs 75.127% | No clear effect |
Closest papers by meaning
- The MegaFace Benchmark: 1 Million Faces for Recognition at Scale (CVPR 2016 · similarity 0.92)
- WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition (CVPR 2021 · similarity 0.86)
- Finding Tiny Faces (CVPR 2017 · similarity 0.85)
- Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors (ICLR 2025 · similarity 0.83)
- TopoFR: A Closer Look at Topology Alignment on Face Recognition (NeurIPS 2024 · similarity 0.83)
- GIF: Generative Inspiration for Face Recognition at Scale (CVPR 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.