Imperial College London

STEFANOS ZAFEIRIOU, PhD

Faculty of EngineeringDepartment of Computing

Reader in Machine Learning and Computer Vision
 
 
 
//

Contact

 

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

 
 
//

Location

 

375Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Deng,
author = {Deng, J and Guo, J and Xue, N and Zafeiriou, S},
publisher = {IEEE},
title = {Arcface: additive angular margin loss for deep face recognition},
url = {http://hdl.handle.net/10044/1/69953},
}

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
PB - IEEE
TI - Arcface: additive angular margin loss for deep face recognition
UR - http://hdl.handle.net/10044/1/69953
ER -