Gicoface: Global Information-Based Cosine Optimal Loss for Deep Face Recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Loss function plays an important role in CNNs. However, the recent loss functions either do not apply weight and feature normalisation or do not explicitly follow the two targets of improving discriminative ability: minimising intra-class variance and maximising inter-class variance. Besides, all of them consider only the feedback information from the current mini-batch instead of the distribution information from the whole training set. In this paper, we propose a novel loss function – Global Information-based Cosine Optimal loss (Gico loss). Gico loss is applied with weight and feature normalisation, designed explicitly following the aforementioned two targets of improving discriminative ability, and is guided by the distribution information from the whole training set. Extensive experiments are conducted on multiple public datasets, which confirms the effectiveness of the proposed Gico loss and shows that we achieve state-of-the-art performance.
LanguageEnglish
Title of host publication2019 IEEE International Conference on Image Processing (ICIP)
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)978-1-5386-6250-2
ISBN (Print)978-1-5386-5249-6
Publication statusPublished - 26 Aug 2019

Publication series

Name2019 IEEE International Conference on Image Processing (ICIP)
PublisherIEEE
ISSN (Print)1522-4880
ISSN (Electronic)2381-8549

Fingerprint

Face recognition
Feedback
Experiments

Cite this

Wei, X., Wang, H., Scotney, B., & Wan, H. (2019). Gicoface: Global Information-Based Cosine Optimal Loss for Deep Face Recognition. In 2019 IEEE International Conference on Image Processing (ICIP) (2019 IEEE International Conference on Image Processing (ICIP)). Institute of Electrical and Electronics Engineers Inc..
Wei, X ; Wang, H. ; Scotney, Bryan ; Wan, Huan. / Gicoface: Global Information-Based Cosine Optimal Loss for Deep Face Recognition. 2019 IEEE International Conference on Image Processing (ICIP). Institute of Electrical and Electronics Engineers Inc., 2019. (2019 IEEE International Conference on Image Processing (ICIP)).
@inproceedings{0479646995d44b58a8dbdd6b00e9797f,
title = "Gicoface: Global Information-Based Cosine Optimal Loss for Deep Face Recognition",
abstract = "Loss function plays an important role in CNNs. However, the recent loss functions either do not apply weight and feature normalisation or do not explicitly follow the two targets of improving discriminative ability: minimising intra-class variance and maximising inter-class variance. Besides, all of them consider only the feedback information from the current mini-batch instead of the distribution information from the whole training set. In this paper, we propose a novel loss function – Global Information-based Cosine Optimal loss (Gico loss). Gico loss is applied with weight and feature normalisation, designed explicitly following the aforementioned two targets of improving discriminative ability, and is guided by the distribution information from the whole training set. Extensive experiments are conducted on multiple public datasets, which confirms the effectiveness of the proposed Gico loss and shows that we achieve state-of-the-art performance.",
author = "X Wei and H. Wang and Bryan Scotney and Huan Wan",
year = "2019",
month = "8",
day = "26",
language = "English",
isbn = "978-1-5386-5249-6",
series = "2019 IEEE International Conference on Image Processing (ICIP)",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE International Conference on Image Processing (ICIP)",
address = "United States",

}

Wei, X, Wang, H, Scotney, B & Wan, H 2019, Gicoface: Global Information-Based Cosine Optimal Loss for Deep Face Recognition. in 2019 IEEE International Conference on Image Processing (ICIP). 2019 IEEE International Conference on Image Processing (ICIP), Institute of Electrical and Electronics Engineers Inc.

Gicoface: Global Information-Based Cosine Optimal Loss for Deep Face Recognition. / Wei, X; Wang, H.; Scotney, Bryan; Wan, Huan.

2019 IEEE International Conference on Image Processing (ICIP). Institute of Electrical and Electronics Engineers Inc., 2019. (2019 IEEE International Conference on Image Processing (ICIP)).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Gicoface: Global Information-Based Cosine Optimal Loss for Deep Face Recognition

AU - Wei, X

AU - Wang, H.

AU - Scotney, Bryan

AU - Wan, Huan

PY - 2019/8/26

Y1 - 2019/8/26

N2 - Loss function plays an important role in CNNs. However, the recent loss functions either do not apply weight and feature normalisation or do not explicitly follow the two targets of improving discriminative ability: minimising intra-class variance and maximising inter-class variance. Besides, all of them consider only the feedback information from the current mini-batch instead of the distribution information from the whole training set. In this paper, we propose a novel loss function – Global Information-based Cosine Optimal loss (Gico loss). Gico loss is applied with weight and feature normalisation, designed explicitly following the aforementioned two targets of improving discriminative ability, and is guided by the distribution information from the whole training set. Extensive experiments are conducted on multiple public datasets, which confirms the effectiveness of the proposed Gico loss and shows that we achieve state-of-the-art performance.

AB - Loss function plays an important role in CNNs. However, the recent loss functions either do not apply weight and feature normalisation or do not explicitly follow the two targets of improving discriminative ability: minimising intra-class variance and maximising inter-class variance. Besides, all of them consider only the feedback information from the current mini-batch instead of the distribution information from the whole training set. In this paper, we propose a novel loss function – Global Information-based Cosine Optimal loss (Gico loss). Gico loss is applied with weight and feature normalisation, designed explicitly following the aforementioned two targets of improving discriminative ability, and is guided by the distribution information from the whole training set. Extensive experiments are conducted on multiple public datasets, which confirms the effectiveness of the proposed Gico loss and shows that we achieve state-of-the-art performance.

M3 - Conference contribution

SN - 978-1-5386-5249-6

T3 - 2019 IEEE International Conference on Image Processing (ICIP)

BT - 2019 IEEE International Conference on Image Processing (ICIP)

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Wei X, Wang H, Scotney B, Wan H. Gicoface: Global Information-Based Cosine Optimal Loss for Deep Face Recognition. In 2019 IEEE International Conference on Image Processing (ICIP). Institute of Electrical and Electronics Engineers Inc. 2019. (2019 IEEE International Conference on Image Processing (ICIP)).