loading
Documents

Research.Publish.Connect.

Paper

Authors: Yan Kong 1 ; Fuzhang Wu 1 ; Feiyue Huang 2 and Yanjun Wu 3

Affiliations: 1 Institute of Software, Chinese Academy of Sciences, Beijing, China ; 2 YouTu Lab, Tencent, China ; 3 State Key Laboratory of Computer Science, Beijing, China

ISBN: 978-989-758-354-4

Keyword(s): Face Recognition, Loss Function, Softmax, Convolutional Neural Network.

Abstract: The face recognition between photos from identification documents (ID, Citizen Card or Passport Card) and daily photos, which is named FRBID(Zhang et al., 2017), is widely used in real world scenarios. However, traditional Softmax loss of deep CNN usually lacks the power of discrimination for FRBID. To address this problem, in this paper, we first revisit recent progress of face recognition losses, and give the theoretical and experimental analysis on the reason why Softmax-like losses work badly on ID-daily face recognition. Then we propose an novel approach named ID-Softmax, which use ID face features as class ’agent’ to guide the deep CNNs to learn highly discriminative features between ID photos and daily photos. In order to promote the ID-daily face recognition, we collect a large dataset ID74K, which includes 74,187 identities with corresponding ID photos and daily photos. To test our approach, we evaluate the feature distribution and face verification performance on dataset ID7 4K. In experiments, we achieve the best performance when comparing with other state-of-the-art methods, which verifies the effectiveness of the proposed ID-Softmax loss. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.205.109.82

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Kong, Y.; Wu, F.; Huang, F. and Wu, Y. (2019). ID-Softmax: A Softmax-like Loss for ID Face Recognition.In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-354-4, pages 412-419. DOI: 10.5220/0007370904120419

@conference{visapp19,
author={Yan Kong. and Fuzhang Wu. and Feiyue Huang. and Yanjun Wu.},
title={ID-Softmax: A Softmax-like Loss for ID Face Recognition},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2019},
pages={412-419},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007370904120419},
isbn={978-989-758-354-4},
}

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - ID-Softmax: A Softmax-like Loss for ID Face Recognition
SN - 978-989-758-354-4
AU - Kong, Y.
AU - Wu, F.
AU - Huang, F.
AU - Wu, Y.
PY - 2019
SP - 412
EP - 419
DO - 10.5220/0007370904120419

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.