Unsupervised Image-to-Image Translation Via Fair Representation of Gender Bias

Sunhee Hwang; Hyeran Byun

doi:10.1109/ICASSP40776.2020.9054129

Unsupervised Image-to-Image Translation Via Fair Representation of Gender Bias

Sunhee Hwang, Hyeran Byun

College of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

Fairness becomes a critical issue of computer vision to reduce discriminative factors in various systems. Among computer vision tasks, Image-to-Image translation for facial attributes editing can yield discriminative results. The unexpected gender changed results can be generated instead of editing target attributes due to the dataset imbalance problem. In this work, we propose a framework of unsupervised Image-to-Image translation that learns a fair representation by separating the latent space of our model into two purposes: 1) Target Attribute Editing, 2) Gender Preserving. We evaluate the proposed framework on CelebA dataset. Both quantitive and qualitative results demonstrate that our method improves image quality and fairness than the prior Image-to-Image translation method.

Original language	English
Title of host publication	2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1953-1957
Number of pages	5
ISBN (Electronic)	9781509066315
DOIs	https://doi.org/10.1109/ICASSP40776.2020.9054129
Publication status	Published - 2020 May
Event	2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Barcelona, Spain Duration: 2020 May 4 → 2020 May 8

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2020-May
ISSN (Print)	1520-6149

Conference

Conference	2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
Country/Territory	Spain
City	Barcelona
Period	20/5/4 → 20/5/8

Bibliographical note

Funding Information:
This work was supported by Institute for Information & communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT) (No. 2019-0-01396, Development of framework for analyzing, detecting, mitigating of bias in AI model and training data)

Publisher Copyright:
© 2020 IEEE.

All Science Journal Classification (ASJC) codes

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP40776.2020.9054129

Cite this

Hwang, S., & Byun, H. (2020). Unsupervised Image-to-Image Translation Via Fair Representation of Gender Bias. In 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings (pp. 1953-1957). [9054129] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2020-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP40776.2020.9054129

Hwang, Sunhee ; Byun, Hyeran. / Unsupervised Image-to-Image Translation Via Fair Representation of Gender Bias. 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 1953-1957 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{2143f9590b884c1c861e6fa73db95973,

title = "Unsupervised Image-to-Image Translation Via Fair Representation of Gender Bias",

abstract = "Fairness becomes a critical issue of computer vision to reduce discriminative factors in various systems. Among computer vision tasks, Image-to-Image translation for facial attributes editing can yield discriminative results. The unexpected gender changed results can be generated instead of editing target attributes due to the dataset imbalance problem. In this work, we propose a framework of unsupervised Image-to-Image translation that learns a fair representation by separating the latent space of our model into two purposes: 1) Target Attribute Editing, 2) Gender Preserving. We evaluate the proposed framework on CelebA dataset. Both quantitive and qualitative results demonstrate that our method improves image quality and fairness than the prior Image-to-Image translation method.",

author = "Sunhee Hwang and Hyeran Byun",

note = "Funding Information: This work was supported by Institute for Information & communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT) (No. 2019-0-01396, Development of framework for analyzing, detecting, mitigating of bias in AI model and training data) Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 ; Conference date: 04-05-2020 Through 08-05-2020",

year = "2020",

month = may,

doi = "10.1109/ICASSP40776.2020.9054129",

language = "English",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1953--1957",

booktitle = "2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings",

address = "United States",

}

Hwang, S & Byun, H 2020, Unsupervised Image-to-Image Translation Via Fair Representation of Gender Bias. in 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings., 9054129, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2020-May, Institute of Electrical and Electronics Engineers Inc., pp. 1953-1957, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, Barcelona, Spain, 20/5/4. https://doi.org/10.1109/ICASSP40776.2020.9054129

Unsupervised Image-to-Image Translation Via Fair Representation of Gender Bias. / Hwang, Sunhee; Byun, Hyeran.

2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. p. 1953-1957 9054129 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2020-May).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Unsupervised Image-to-Image Translation Via Fair Representation of Gender Bias

AU - Hwang, Sunhee

AU - Byun, Hyeran

N1 - Funding Information: This work was supported by Institute for Information & communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT) (No. 2019-0-01396, Development of framework for analyzing, detecting, mitigating of bias in AI model and training data) Publisher Copyright: © 2020 IEEE.

PY - 2020/5

Y1 - 2020/5

N2 - Fairness becomes a critical issue of computer vision to reduce discriminative factors in various systems. Among computer vision tasks, Image-to-Image translation for facial attributes editing can yield discriminative results. The unexpected gender changed results can be generated instead of editing target attributes due to the dataset imbalance problem. In this work, we propose a framework of unsupervised Image-to-Image translation that learns a fair representation by separating the latent space of our model into two purposes: 1) Target Attribute Editing, 2) Gender Preserving. We evaluate the proposed framework on CelebA dataset. Both quantitive and qualitative results demonstrate that our method improves image quality and fairness than the prior Image-to-Image translation method.

AB - Fairness becomes a critical issue of computer vision to reduce discriminative factors in various systems. Among computer vision tasks, Image-to-Image translation for facial attributes editing can yield discriminative results. The unexpected gender changed results can be generated instead of editing target attributes due to the dataset imbalance problem. In this work, we propose a framework of unsupervised Image-to-Image translation that learns a fair representation by separating the latent space of our model into two purposes: 1) Target Attribute Editing, 2) Gender Preserving. We evaluate the proposed framework on CelebA dataset. Both quantitive and qualitative results demonstrate that our method improves image quality and fairness than the prior Image-to-Image translation method.

UR - http://www.scopus.com/inward/record.url?scp=85089244960&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85089244960&partnerID=8YFLogxK

U2 - 10.1109/ICASSP40776.2020.9054129

DO - 10.1109/ICASSP40776.2020.9054129

M3 - Conference contribution

AN - SCOPUS:85089244960

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 1953

EP - 1957

BT - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020

Y2 - 4 May 2020 through 8 May 2020

ER -

Hwang S, Byun H. Unsupervised Image-to-Image Translation Via Fair Representation of Gender Bias. In 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. p. 1953-1957. 9054129. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP40776.2020.9054129

Unsupervised Image-to-Image Translation Via Fair Representation of Gender Bias

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this