Face Generation for Low-Shot Learning Using Generative Adversarial Networks

Junsuk Choe, Song Park, Kyungmin Kim, Joo Hyun Park, Dongseob Kim, Hyunjung Shim

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

8 Citations (Scopus)

Abstract

Recently, low-shot learning has been proposed for handling the lack of training data in machine learning. Despite of the importance of this issue, relatively less efforts have been made to study this problem. In this paper, we aim to increase the size of training dataset in various ways to improve the accuracy and robustness of face recognition. In detail, we adapt a generator from the Generative Adversarial Network (GAN) to increase the size of training dataset, which includes a base set, a widely available dataset, and a novel set, a given limited dataset, while adopting transfer learning as a backend. Based on extensive experimental study, we conduct the analysis on various data augmentation methods, observing how each affects the identification accuracy. Finally, we conclude that the proposed algorithm for generating faces is effective in improving the identification accuracy and coverage at the precision of 99% using both the base and novel set.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1940-1948
Number of pages9
ISBN (Electronic)9781538610343
DOIs
Publication statusPublished - 2017 Jul 1
Event16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 - Venice, Italy
Duration: 2017 Oct 222017 Oct 29

Publication series

NameProceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
Volume2018-January

Other

Other16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017
CountryItaly
CityVenice
Period17/10/2217/10/29

Fingerprint

Face recognition
Learning systems

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Choe, J., Park, S., Kim, K., Park, J. H., Kim, D., & Shim, H. (2017). Face Generation for Low-Shot Learning Using Generative Adversarial Networks. In Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017 (pp. 1940-1948). (Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW.2017.229
Choe, Junsuk ; Park, Song ; Kim, Kyungmin ; Park, Joo Hyun ; Kim, Dongseob ; Shim, Hyunjung. / Face Generation for Low-Shot Learning Using Generative Adversarial Networks. Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1940-1948 (Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017).
@inproceedings{f954de59499f4301be4f865f142a42de,
title = "Face Generation for Low-Shot Learning Using Generative Adversarial Networks",
abstract = "Recently, low-shot learning has been proposed for handling the lack of training data in machine learning. Despite of the importance of this issue, relatively less efforts have been made to study this problem. In this paper, we aim to increase the size of training dataset in various ways to improve the accuracy and robustness of face recognition. In detail, we adapt a generator from the Generative Adversarial Network (GAN) to increase the size of training dataset, which includes a base set, a widely available dataset, and a novel set, a given limited dataset, while adopting transfer learning as a backend. Based on extensive experimental study, we conduct the analysis on various data augmentation methods, observing how each affects the identification accuracy. Finally, we conclude that the proposed algorithm for generating faces is effective in improving the identification accuracy and coverage at the precision of 99{\%} using both the base and novel set.",
author = "Junsuk Choe and Song Park and Kyungmin Kim and Park, {Joo Hyun} and Dongseob Kim and Hyunjung Shim",
year = "2017",
month = "7",
day = "1",
doi = "10.1109/ICCVW.2017.229",
language = "English",
series = "Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1940--1948",
booktitle = "Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017",
address = "United States",

}

Choe, J, Park, S, Kim, K, Park, JH, Kim, D & Shim, H 2017, Face Generation for Low-Shot Learning Using Generative Adversarial Networks. in Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1940-1948, 16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017, Venice, Italy, 17/10/22. https://doi.org/10.1109/ICCVW.2017.229

Face Generation for Low-Shot Learning Using Generative Adversarial Networks. / Choe, Junsuk; Park, Song; Kim, Kyungmin; Park, Joo Hyun; Kim, Dongseob; Shim, Hyunjung.

Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1940-1948 (Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017; Vol. 2018-January).

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

TY - GEN

T1 - Face Generation for Low-Shot Learning Using Generative Adversarial Networks

AU - Choe, Junsuk

AU - Park, Song

AU - Kim, Kyungmin

AU - Park, Joo Hyun

AU - Kim, Dongseob

AU - Shim, Hyunjung

PY - 2017/7/1

Y1 - 2017/7/1

N2 - Recently, low-shot learning has been proposed for handling the lack of training data in machine learning. Despite of the importance of this issue, relatively less efforts have been made to study this problem. In this paper, we aim to increase the size of training dataset in various ways to improve the accuracy and robustness of face recognition. In detail, we adapt a generator from the Generative Adversarial Network (GAN) to increase the size of training dataset, which includes a base set, a widely available dataset, and a novel set, a given limited dataset, while adopting transfer learning as a backend. Based on extensive experimental study, we conduct the analysis on various data augmentation methods, observing how each affects the identification accuracy. Finally, we conclude that the proposed algorithm for generating faces is effective in improving the identification accuracy and coverage at the precision of 99% using both the base and novel set.

AB - Recently, low-shot learning has been proposed for handling the lack of training data in machine learning. Despite of the importance of this issue, relatively less efforts have been made to study this problem. In this paper, we aim to increase the size of training dataset in various ways to improve the accuracy and robustness of face recognition. In detail, we adapt a generator from the Generative Adversarial Network (GAN) to increase the size of training dataset, which includes a base set, a widely available dataset, and a novel set, a given limited dataset, while adopting transfer learning as a backend. Based on extensive experimental study, we conduct the analysis on various data augmentation methods, observing how each affects the identification accuracy. Finally, we conclude that the proposed algorithm for generating faces is effective in improving the identification accuracy and coverage at the precision of 99% using both the base and novel set.

UR - http://www.scopus.com/inward/record.url?scp=85046262389&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046262389&partnerID=8YFLogxK

U2 - 10.1109/ICCVW.2017.229

DO - 10.1109/ICCVW.2017.229

M3 - Conference contribution

AN - SCOPUS:85046262389

T3 - Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017

SP - 1940

EP - 1948

BT - Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Choe J, Park S, Kim K, Park JH, Kim D, Shim H. Face Generation for Low-Shot Learning Using Generative Adversarial Networks. In Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1940-1948. (Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017). https://doi.org/10.1109/ICCVW.2017.229