Laplacian Pyramid-like Autoencoder

Sangjun Han; Taeil Hur; Youngmi Hur

doi:10.1007/978-3-031-10464-0_5

Laplacian Pyramid-like Autoencoder

Sangjun Han, Taeil Hur, Youngmi Hur

Department of Mathematics

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

Abstract

In this paper, we develop the Laplacian pyramid-like autoencoder (LPAE) by adding the Laplacian pyramid (LP) concept widely used to analyze images in Signal Processing. LPAE decomposes an image into the approximation image and the detail image in the encoder part and then tries to reconstruct the original image in the decoder part using the two components. We use LPAE for experiments on classifications and super-resolution areas. Using the detail image and the smaller-sized approximation image as inputs of a classification network, our LPAE makes the model lighter. Moreover, we show that the performance of the connected classification networks has remained substantially high. In a super-resolution area, we show that the decoder part gets a high-quality reconstruction image by setting to resemble the structure of LP. Consequently, LPAE improves the original results by combining the decoder part of the autoencoder and the super-resolution network.

Original language	English
Title of host publication	Intelligent Computing - Proceedings of the 2022 Computing Conference
Editors	Kohei Arai
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	59-78
Number of pages	20
ISBN (Print)	9783031104633
DOIs	https://doi.org/10.1007/978-3-031-10464-0_5
Publication status	Published - 2022
Event	Computing Conference, 2022 - Virtual, Online Duration: 2022 Jul 14 → 2022 Jul 15

Publication series

Name	Lecture Notes in Networks and Systems
Volume	507 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	Computing Conference, 2022
City	Virtual, Online
Period	22/7/14 → 22/7/15

Bibliographical note

Funding Information:
Y. Hur—This work was supported in part by National Research Foundation of Korea (NRF) [Grant Numbers 2015R1A5A1009350 and 2021R1A2C1007598], and by the ‘Ministry of Science and ICT’ and NIPA via “HPC Support” Project.

Funding Information:
Acknowledgments. T. Hur—This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No.2021-0-00023, Developing a lightweight Korean text detection and recognition technology for complex disaster situations).

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
Signal Processing
Computer Networks and Communications

Access to Document

10.1007/978-3-031-10464-0_5

Cite this

@inproceedings{e77ca60d1293414f9ad968ea4f95a9fa,

title = "Laplacian Pyramid-like Autoencoder",

abstract = "In this paper, we develop the Laplacian pyramid-like autoencoder (LPAE) by adding the Laplacian pyramid (LP) concept widely used to analyze images in Signal Processing. LPAE decomposes an image into the approximation image and the detail image in the encoder part and then tries to reconstruct the original image in the decoder part using the two components. We use LPAE for experiments on classifications and super-resolution areas. Using the detail image and the smaller-sized approximation image as inputs of a classification network, our LPAE makes the model lighter. Moreover, we show that the performance of the connected classification networks has remained substantially high. In a super-resolution area, we show that the decoder part gets a high-quality reconstruction image by setting to resemble the structure of LP. Consequently, LPAE improves the original results by combining the decoder part of the autoencoder and the super-resolution network.",

author = "Sangjun Han and Taeil Hur and Youngmi Hur",

note = "Funding Information: Y. Hur—This work was supported in part by National Research Foundation of Korea (NRF) [Grant Numbers 2015R1A5A1009350 and 2021R1A2C1007598], and by the {\textquoteleft}Ministry of Science and ICT{\textquoteright} and NIPA via “HPC Support” Project. Funding Information: Acknowledgments. T. Hur—This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No.2021-0-00023, Developing a lightweight Korean text detection and recognition technology for complex disaster situations). Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; Computing Conference, 2022 ; Conference date: 14-07-2022 Through 15-07-2022",

year = "2022",

doi = "10.1007/978-3-031-10464-0_5",

language = "English",

isbn = "9783031104633",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "59--78",

editor = "Kohei Arai",

booktitle = "Intelligent Computing - Proceedings of the 2022 Computing Conference",

address = "Germany",

}

Laplacian Pyramid-like Autoencoder. / Han, Sangjun; Hur, Taeil; Hur, Youngmi.
Intelligent Computing - Proceedings of the 2022 Computing Conference. ed. / Kohei Arai. Springer Science and Business Media Deutschland GmbH, 2022. p. 59-78 (Lecture Notes in Networks and Systems; Vol. 507 LNNS).

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

TY - GEN

T1 - Laplacian Pyramid-like Autoencoder

AU - Han, Sangjun

AU - Hur, Taeil

AU - Hur, Youngmi

N1 - Funding Information: Y. Hur—This work was supported in part by National Research Foundation of Korea (NRF) [Grant Numbers 2015R1A5A1009350 and 2021R1A2C1007598], and by the ‘Ministry of Science and ICT’ and NIPA via “HPC Support” Project. Funding Information: Acknowledgments. T. Hur—This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No.2021-0-00023, Developing a lightweight Korean text detection and recognition technology for complex disaster situations). Publisher Copyright: © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

PY - 2022

Y1 - 2022

N2 - In this paper, we develop the Laplacian pyramid-like autoencoder (LPAE) by adding the Laplacian pyramid (LP) concept widely used to analyze images in Signal Processing. LPAE decomposes an image into the approximation image and the detail image in the encoder part and then tries to reconstruct the original image in the decoder part using the two components. We use LPAE for experiments on classifications and super-resolution areas. Using the detail image and the smaller-sized approximation image as inputs of a classification network, our LPAE makes the model lighter. Moreover, we show that the performance of the connected classification networks has remained substantially high. In a super-resolution area, we show that the decoder part gets a high-quality reconstruction image by setting to resemble the structure of LP. Consequently, LPAE improves the original results by combining the decoder part of the autoencoder and the super-resolution network.

AB - In this paper, we develop the Laplacian pyramid-like autoencoder (LPAE) by adding the Laplacian pyramid (LP) concept widely used to analyze images in Signal Processing. LPAE decomposes an image into the approximation image and the detail image in the encoder part and then tries to reconstruct the original image in the decoder part using the two components. We use LPAE for experiments on classifications and super-resolution areas. Using the detail image and the smaller-sized approximation image as inputs of a classification network, our LPAE makes the model lighter. Moreover, we show that the performance of the connected classification networks has remained substantially high. In a super-resolution area, we show that the decoder part gets a high-quality reconstruction image by setting to resemble the structure of LP. Consequently, LPAE improves the original results by combining the decoder part of the autoencoder and the super-resolution network.

UR - http://www.scopus.com/inward/record.url?scp=85135098285&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85135098285&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-10464-0_5

DO - 10.1007/978-3-031-10464-0_5

M3 - Conference contribution

AN - SCOPUS:85135098285

SN - 9783031104633

T3 - Lecture Notes in Networks and Systems

SP - 59

EP - 78

BT - Intelligent Computing - Proceedings of the 2022 Computing Conference

A2 - Arai, Kohei

PB - Springer Science and Business Media Deutschland GmbH

T2 - Computing Conference, 2022

Y2 - 14 July 2022 through 15 July 2022

ER -

Laplacian Pyramid-like Autoencoder

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this