Imperial College London
Alternate

STEFANOS ZAFEIRIOU, PhD

Faculty of Engineering, Department of Computing

Professor in Machine Learning & Computer Vision
 
 
 
//

Contact

 

+44 (0)20 7594 8461s.zafeiriou Website CV

 
 
//

Location

 

375Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Deng:2020:10.1109/CVPR.2019.00482,
author = {Deng, J and Guo, J and Xue, N and Zafeiriou, S},
doi = {10.1109/CVPR.2019.00482},
pages = {4685--4694},
publisher = {IEEE},
title = {Arcface: additive angular margin loss for deep face recognition},
url = {http://dx.doi.org/10.1109/CVPR.2019.00482},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - One  of  the  main  challenges  in  feature  learning  usingDeep Convolutional Neural Networks (DCNNs) for large-scale face recognition is the design of appropriate loss func-tions  that  enhance  discriminative  power.   Centre  loss  pe-nalises the distance between the deep features and their cor-responding class centres in the Euclidean space to achieveintra-class compactness.  SphereFace assumes that the lin-ear transformation matrix in the last fully connected layercan be used as a representation of the class centres in anangular space and penalises the angles between the deepfeatures and their corresponding weights in a multiplicativeway.  Recently, a popular line of research is to incorporatemargins in well-established loss functions in order to max-imise face class separability.  In this paper, we propose anAdditive Angular Margin Loss (ArcFace) to obtain highlydiscriminative features for face recognition.  The proposedArcFace has a clear geometric interpretation due to the ex-act correspondence to the geodesic distance on the hyper-sphere. We present arguably the most extensive experimen-tal evaluation of all the recent state-of-the-art face recog-nition methods on over 10 face recognition benchmarks in-cluding a new large-scale image database with trillion levelof pairs and a large-scale video dataset.  We show that Ar-cFace consistently outperforms the state-of-the-art and canbe easily implemented with negligible computational over-head.  We release all refined training data, training codes,pre-trained models and training logs1, which will help re-produce the results in this paper.
AU  - Deng,J
AU  - Guo,J
AU  - Xue,N
AU  - Zafeiriou,S
DO  - 10.1109/CVPR.2019.00482
EP  - 4694
PB  - IEEE
PY  - 2020///
SN  - 2575-7075
SP  - 4685
TI  - Arcface: additive angular margin loss for deep face recognition
UR  - http://dx.doi.org/10.1109/CVPR.2019.00482
UR  - http://hdl.handle.net/10044/1/69953
ER  -
Download