MagFace

MagFace: A Universal Representation for Face Recognition and Quality Assessment
in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021, Oral presentation

Paper: arXiv (NOTE: Figure 2 in the arxiv version is incorrect and will be fixed later. Use the above one instead.)

A toy example: examples.ipynb

Poster: GoogleDrive, BaiduDrive code: dt9e

Presentation: TBD

CheckPoint: GoogleDrive, BaiduDrive code: wsw3

NOTE: The original codes are implemented on a private codebase and will not be released.
This repo is an official but abridged version. See todo list for plans.

BibTex

@inproceedings{meng2021magface,
  title={MagFace: A universal representation for face recognition and quality assessment},
  author={Meng, Qiang and Zhao, Shichao and Huang, Zhida and Zhou, Feng},
  booktitle=IEEE Conference on Computer Vision and Pattern Recognition,
  year=2021
}

Usage

  1. Prepare a training list with format imgname 0 id 0 in each line, as indicated here.
  2. Modify parameters in run/run.sh and run it!
cd run/
./run.sh

GitHub

https://github.com/IrvingMeng/MagFace