Arcface: additive angular margin loss for deep face recognition
File(s)
Accepted version
Author(s)
Deng, Jiankang
Guo, Jia
Xue, Niannan
Zafeiriou, Stefanos
Type
Conference Paper
Abstract
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.
Date Issued
2020-01-09
Date Acceptance
2019-03-11
Citation
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp.4685-4694
ISBN
9781728132938
ISSN
2575-7075
Publisher
IEEE
Start Page
4685
End Page
4694
Journal / Book Title
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Copyright Statement
© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor
Engineering & Physical Science Research Council (E
Engineering & Physical Science Research Council (EPSRC)
Grant Number
EP/N007743/1
EP/S010203/1
Source
CVPR 2019
Subjects
Science & Technology
Technology
Computer Science, Artificial Intelligence
Computer Science, Theory & Methods
Computer Science
Publication Status
Published
Start Date
2019-06-16
Finish Date
2019-06-20
Coverage Spatial
California, CA, USA
Date Publish Online
2020-01-09