Efficient Deep Learning-Based Lossy Image Compression Via Asymmetric Autoencoder and Pruning

Jun Hyuk Kim; Jun Ho Choi; Jaehyuk Chang; Jong Seok Lee

doi:10.1109/ICASSP40776.2020.9053102

Efficient Deep Learning-Based Lossy Image Compression Via Asymmetric Autoencoder and Pruning

Jun Hyuk Kim, Jun Ho Choi, Jaehyuk Chang, Jong Seok Lee

School of Integrated Technology

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

21 Citations (Scopus)

Abstract

Recently, deep learning-based lossy image compression methods have been proposed. However, their efficiency in terms of storage and computational costs has not been addressed adequately. In this paper, we propose efficient lossy image compression methods based on asymmetric autoencoder and decoder pruning. Experimental results demonstrate the effectiveness of our methods.

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	2063-2067
Number of pages	5
ISBN (Electronic)	9781509066315
DOIs	https://doi.org/10.1109/ICASSP40776.2020.9053102
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

Publisher Copyright:
© 2020 IEEE.

All Science Journal Classification (ASJC) codes

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP40776.2020.9053102

Cite this

Kim, J. H., Choi, J. H., Chang, J., & Lee, J. S. (2020). Efficient Deep Learning-Based Lossy Image Compression Via Asymmetric Autoencoder and Pruning. In 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings (pp. 2063-2067). Article 9053102 (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/ICASSP40776.2020.9053102

Kim, Jun Hyuk ; Choi, Jun Ho ; Chang, Jaehyuk et al. / Efficient Deep Learning-Based Lossy Image Compression Via Asymmetric Autoencoder and Pruning. 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 2063-2067 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{ea0a43df047f44768a206ec11ea2a145,

title = "Efficient Deep Learning-Based Lossy Image Compression Via Asymmetric Autoencoder and Pruning",

abstract = "Recently, deep learning-based lossy image compression methods have been proposed. However, their efficiency in terms of storage and computational costs has not been addressed adequately. In this paper, we propose efficient lossy image compression methods based on asymmetric autoencoder and decoder pruning. Experimental results demonstrate the effectiveness of our methods.",

keywords = "Lossy image compression, asymmetric autoencoder, filter pruning, weight pruning",

author = "Kim, {Jun Hyuk} and Choi, {Jun Ho} and Jaehyuk Chang and Lee, {Jong Seok}",

note = "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/ICASSP40776.2020.9053102",

language = "English",

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

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

pages = "2063--2067",

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

address = "United States",

}

Kim, JH, Choi, JH, Chang, J & Lee, JS 2020, Efficient Deep Learning-Based Lossy Image Compression Via Asymmetric Autoencoder and Pruning. in 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings., 9053102, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2020-May, Institute of Electrical and Electronics Engineers Inc., pp. 2063-2067, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, Barcelona, Spain, 20/5/4. https://doi.org/10.1109/ICASSP40776.2020.9053102

Efficient Deep Learning-Based Lossy Image Compression Via Asymmetric Autoencoder and Pruning. / Kim, Jun Hyuk; Choi, Jun Ho; Chang, Jaehyuk et al.
2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. p. 2063-2067 9053102 (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 - Efficient Deep Learning-Based Lossy Image Compression Via Asymmetric Autoencoder and Pruning

AU - Kim, Jun Hyuk

AU - Choi, Jun Ho

AU - Chang, Jaehyuk

AU - Lee, Jong Seok

PY - 2020/5

Y1 - 2020/5

N2 - Recently, deep learning-based lossy image compression methods have been proposed. However, their efficiency in terms of storage and computational costs has not been addressed adequately. In this paper, we propose efficient lossy image compression methods based on asymmetric autoencoder and decoder pruning. Experimental results demonstrate the effectiveness of our methods.

AB - Recently, deep learning-based lossy image compression methods have been proposed. However, their efficiency in terms of storage and computational costs has not been addressed adequately. In this paper, we propose efficient lossy image compression methods based on asymmetric autoencoder and decoder pruning. Experimental results demonstrate the effectiveness of our methods.

KW - Lossy image compression

KW - asymmetric autoencoder

KW - filter pruning

KW - weight pruning

UR - http://www.scopus.com/inward/record.url?scp=85089211418&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85089211418&partnerID=8YFLogxK

U2 - 10.1109/ICASSP40776.2020.9053102

DO - 10.1109/ICASSP40776.2020.9053102

M3 - Conference contribution

AN - SCOPUS:85089211418

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

SP - 2063

EP - 2067

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 -

Kim JH, Choi JH, Chang J, Lee JS. Efficient Deep Learning-Based Lossy Image Compression Via Asymmetric Autoencoder and Pruning. In 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. p. 2063-2067. 9053102. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP40776.2020.9053102

Efficient Deep Learning-Based Lossy Image Compression Via Asymmetric Autoencoder and Pruning

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this