Manipulating Neural Network Block for Robust Image Segmentation

Hyungjoon Kim; Hyeonwoo Kim; Seongkuk Cho; Eenjun Hwang

doi:10.1109/BigComp54360.2022.00054

Manipulating Neural Network Block for Robust Image Segmentation

Hyungjoon Kim, Hyeonwoo Kim, Seongkuk Cho, Eenjun Hwang

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

1 Citation (Scopus)

Abstract

Convolutional neural networks have presented a new paradigm in the field of computer vision, but their fixed convolutional filter size causes long-range dependency loss problems. Also, because of the equal importance of all convolution filters, unnecessary information is included in the convolution result. These problems are more serious in image segmentation, where every pixel is labeled, as opposed to image classification or object recognition. In this paper, to alleviate these problems, we propose an attention-based neural network block that extracts robust features including channel and spatial information. The proposed block calculates the pixel relationship on a unit channel and then calculates the importance among channels. To evaluate the effectiveness of the proposed blocks, we constructed segmentation models by applying the proposed blocks to well-known network and measures their segmentation accuracy. We report some of the results.

Original language	English
Title of host publication	Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022
Editors	Herwig Unger, Young-Kuk Kim, Eenjun Hwang, Sung-Bae Cho, Stephan Pareigis, Kyamakya Kyandoghere, Young-Guk Ha, Jinho Kim, Atsuyuki Morishima, Christian Wagner, Hyuk-Yoon Kwon, Yang-Sae Moon, Carson Leung
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	246-250
Number of pages	5
ISBN (Electronic)	9781665421973
DOIs	https://doi.org/10.1109/BigComp54360.2022.00054
Publication status	Published - 2022
Event	2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022 - Daegu, Korea, Republic of Duration: 2022 Jan 17 → 2022 Jan 20

Publication series

Name	Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022

Conference

Conference	2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022
Country/Territory	Korea, Republic of
City	Daegu
Period	22/1/17 → 22/1/20

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT)(No. NRF-2021R1A4A1031864)

Publisher Copyright:
© 2022 IEEE.

Keywords

Attention mechanism
Convolutional Neural Networks
Feature extraction
Image segmentation

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Computer Vision and Pattern Recognition
Information Systems and Management
Health Informatics

Access to Document

10.1109/BigComp54360.2022.00054

Cite this

Kim, H., Kim, H., Cho, S., & Hwang, E. (2022). Manipulating Neural Network Block for Robust Image Segmentation. In H. Unger, Y.-K. Kim, E. Hwang, S.-B. Cho, S. Pareigis, K. Kyandoghere, Y.-G. Ha, J. Kim, A. Morishima, C. Wagner, H.-Y. Kwon, Y.-S. Moon, & C. Leung (Eds.), Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022 (pp. 246-250). (Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BigComp54360.2022.00054

Manipulating Neural Network Block for Robust Image Segmentation. / Kim, Hyungjoon; Kim, Hyeonwoo; Cho, Seongkuk et al.
Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022. ed. / Herwig Unger; Young-Kuk Kim; Eenjun Hwang; Sung-Bae Cho; Stephan Pareigis; Kyamakya Kyandoghere; Young-Guk Ha; Jinho Kim; Atsuyuki Morishima; Christian Wagner; Hyuk-Yoon Kwon; Yang-Sae Moon; Carson Leung. Institute of Electrical and Electronics Engineers Inc., 2022. p. 246-250 (Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022).

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

Kim, H, Kim, H, Cho, S & Hwang, E 2022, Manipulating Neural Network Block for Robust Image Segmentation. in H Unger, Y-K Kim, E Hwang, S-B Cho, S Pareigis, K Kyandoghere, Y-G Ha, J Kim, A Morishima, C Wagner, H-Y Kwon, Y-S Moon & C Leung (eds), Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022. Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022, Institute of Electrical and Electronics Engineers Inc., pp. 246-250, 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022, Daegu, Korea, Republic of, 22/1/17. https://doi.org/10.1109/BigComp54360.2022.00054

Kim H, Kim H, Cho S, Hwang E. Manipulating Neural Network Block for Robust Image Segmentation. In Unger H, Kim YK, Hwang E, Cho SB, Pareigis S, Kyandoghere K, Ha YG, Kim J, Morishima A, Wagner C, Kwon HY, Moon YS, Leung C, editors, Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 246-250. (Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022). doi: 10.1109/BigComp54360.2022.00054

Kim, Hyungjoon ; Kim, Hyeonwoo ; Cho, Seongkuk et al. / Manipulating Neural Network Block for Robust Image Segmentation. Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022. editor / Herwig Unger ; Young-Kuk Kim ; Eenjun Hwang ; Sung-Bae Cho ; Stephan Pareigis ; Kyamakya Kyandoghere ; Young-Guk Ha ; Jinho Kim ; Atsuyuki Morishima ; Christian Wagner ; Hyuk-Yoon Kwon ; Yang-Sae Moon ; Carson Leung. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 246-250 (Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022).

@inproceedings{86c21c3ffa6c4095baa8f9c0fa777f55,

title = "Manipulating Neural Network Block for Robust Image Segmentation",

abstract = "Convolutional neural networks have presented a new paradigm in the field of computer vision, but their fixed convolutional filter size causes long-range dependency loss problems. Also, because of the equal importance of all convolution filters, unnecessary information is included in the convolution result. These problems are more serious in image segmentation, where every pixel is labeled, as opposed to image classification or object recognition. In this paper, to alleviate these problems, we propose an attention-based neural network block that extracts robust features including channel and spatial information. The proposed block calculates the pixel relationship on a unit channel and then calculates the importance among channels. To evaluate the effectiveness of the proposed blocks, we constructed segmentation models by applying the proposed blocks to well-known network and measures their segmentation accuracy. We report some of the results. ",

keywords = "Attention mechanism, Convolutional Neural Networks, Feature extraction, Image segmentation",

author = "Hyungjoon Kim and Hyeonwoo Kim and Seongkuk Cho and Eenjun Hwang",

note = "Funding Information: ACKNOWLEDGMENT This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT)(No. NRF-2021R1A4A1031864) Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022 ; Conference date: 17-01-2022 Through 20-01-2022",

year = "2022",

doi = "10.1109/BigComp54360.2022.00054",

language = "English",

series = "Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022",

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

pages = "246--250",

editor = "Herwig Unger and Young-Kuk Kim and Eenjun Hwang and Sung-Bae Cho and Stephan Pareigis and Kyamakya Kyandoghere and Young-Guk Ha and Jinho Kim and Atsuyuki Morishima and Christian Wagner and Hyuk-Yoon Kwon and Yang-Sae Moon and Carson Leung",

booktitle = "Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022",

}

TY - GEN

T1 - Manipulating Neural Network Block for Robust Image Segmentation

AU - Kim, Hyungjoon

AU - Kim, Hyeonwoo

AU - Cho, Seongkuk

AU - Hwang, Eenjun

N1 - Funding Information: ACKNOWLEDGMENT This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT)(No. NRF-2021R1A4A1031864) Publisher Copyright: © 2022 IEEE.

PY - 2022

Y1 - 2022

N2 - Convolutional neural networks have presented a new paradigm in the field of computer vision, but their fixed convolutional filter size causes long-range dependency loss problems. Also, because of the equal importance of all convolution filters, unnecessary information is included in the convolution result. These problems are more serious in image segmentation, where every pixel is labeled, as opposed to image classification or object recognition. In this paper, to alleviate these problems, we propose an attention-based neural network block that extracts robust features including channel and spatial information. The proposed block calculates the pixel relationship on a unit channel and then calculates the importance among channels. To evaluate the effectiveness of the proposed blocks, we constructed segmentation models by applying the proposed blocks to well-known network and measures their segmentation accuracy. We report some of the results.

AB - Convolutional neural networks have presented a new paradigm in the field of computer vision, but their fixed convolutional filter size causes long-range dependency loss problems. Also, because of the equal importance of all convolution filters, unnecessary information is included in the convolution result. These problems are more serious in image segmentation, where every pixel is labeled, as opposed to image classification or object recognition. In this paper, to alleviate these problems, we propose an attention-based neural network block that extracts robust features including channel and spatial information. The proposed block calculates the pixel relationship on a unit channel and then calculates the importance among channels. To evaluate the effectiveness of the proposed blocks, we constructed segmentation models by applying the proposed blocks to well-known network and measures their segmentation accuracy. We report some of the results.

KW - Attention mechanism

KW - Convolutional Neural Networks

KW - Feature extraction

KW - Image segmentation

UR - http://www.scopus.com/inward/record.url?scp=85124263263&partnerID=8YFLogxK

U2 - 10.1109/BigComp54360.2022.00054

DO - 10.1109/BigComp54360.2022.00054

M3 - Conference contribution

AN - SCOPUS:85124263263

T3 - Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022

SP - 246

EP - 250

BT - Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022

A2 - Unger, Herwig

A2 - Kim, Young-Kuk

A2 - Hwang, Eenjun

A2 - Cho, Sung-Bae

A2 - Pareigis, Stephan

A2 - Kyandoghere, Kyamakya

A2 - Ha, Young-Guk

A2 - Kim, Jinho

A2 - Morishima, Atsuyuki

A2 - Wagner, Christian

A2 - Kwon, Hyuk-Yoon

A2 - Moon, Yang-Sae

A2 - Leung, Carson

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022

Y2 - 17 January 2022 through 20 January 2022

ER -

Manipulating Neural Network Block for Robust Image Segmentation

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this