AI Paper Atlas

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

ECCV 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 2,149 citations (OpenAlex)

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 changedWhereMeasuredEffect
use Random-set image instead of Hard-set image per celebritybaseline CNN · MS-Celeb-1M measurement set (500 celebrities)coverage at precision 95%: 0.442 -> 0.728Improved
raise required precision from 95% to 99%baseline CNN · MS-Celeb-1M Hard setcoverage: 0.442 -> 0.052Hurt
raise required precision from 95% to 99%baseline CNN · MS-Celeb-1M Random setcoverage: 0.728 -> 0.606Hurt
sample measurement celebrities with weight f^(1/sqrt(5)) instead of f (ablation)measurement set construction · MS-Celeb-1M celebrity listshare 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 trainingtraining convergenceImproved
initialize the small model from a pre-trained model (ablation)baseline CNN · MS-Celeb-1M trainingconvergence speedImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy