A review and comparison of convolution neural network models under a unified framework

Jimin Park; Yoonsuh Jung

doi:10.29220/CSAM.2022.29.2.161

A review and comparison of convolution neural network models under a unified framework

Jimin Park, Yoonsuh Jung

Research output: Contribution to journal › Article › peer-review

7 Citations (Scopus)

Abstract

There has been active research in image classification using deep learning convolutional neural network (CNN) models. ImageNet large-scale visual recognition challenge (ILSVRC) (2010-2017) was one of the most important competitions that boosted the development of efficient deep learning algorithms. This paper introduces and compares six monumental models that achieved high prediction accuracy in ILSVRC. First, we provide a review of the models to illustrate their unique structure and characteristics of the models. We then compare those models under a unified framework. For this reason, additional devices that are not crucial to the structure are excluded. Four popular data sets with different characteristics are then considered to measure the prediction accuracy. By investigating the characteristics of the data sets and the models being compared, we provide some insight into the architectural features of the models.

Original language	English
Pages (from-to)	161-176
Number of pages	16
Journal	Communications for Statistical Applications and Methods
Volume	29
Issue number	2
DOIs	https://doi.org/10.29220/CSAM.2022.29.2.161
Publication status	Published - 2022 Mar

Bibliographical note

Funding Information:
Yoonsuh Jung’s work was partially supported by National Research Foundation of Korea (NRF) grant funded by Korea government (MIST)(2019R1A4A1028134 and 2021R1F1A1062347).

Funding Information:
Jung’s work has been partially supported by National Research Foundation of Korea (NRF) grants funded by the Korea government(MIST) 2019R1A4A1028134 and 2021R1F1A1062347. 1Corresponding author: Department of Statistics, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, South Korea. E-mail: [email protected]

Publisher Copyright:
© 2022. The Korean Statistical Society, and Korean International Statistical Society. All rights reserved

Keywords

Classification
ImageNet large-scale visual recog nition challenge (ILSVRC)
convolutional neural network (CNN)
image data

ASJC Scopus subject areas

Statistics and Probability
Modelling and Simulation
Finance
Statistics, Probability and Uncertainty
Applied Mathematics

Access to Document

10.29220/CSAM.2022.29.2.161

Cite this

@article{e998f57bcfaa4192a4b6b752587ccd67,

title = "A review and comparison of convolution neural network models under a unified framework",

abstract = "There has been active research in image classification using deep learning convolutional neural network (CNN) models. ImageNet large-scale visual recognition challenge (ILSVRC) (2010-2017) was one of the most important competitions that boosted the development of efficient deep learning algorithms. This paper introduces and compares six monumental models that achieved high prediction accuracy in ILSVRC. First, we provide a review of the models to illustrate their unique structure and characteristics of the models. We then compare those models under a unified framework. For this reason, additional devices that are not crucial to the structure are excluded. Four popular data sets with different characteristics are then considered to measure the prediction accuracy. By investigating the characteristics of the data sets and the models being compared, we provide some insight into the architectural features of the models.",

keywords = "Classification, ImageNet large-scale visual recog nition challenge (ILSVRC), convolutional neural network (CNN), image data",

author = "Jimin Park and Yoonsuh Jung",

note = "Funding Information: Yoonsuh Jung{\textquoteright}s work was partially supported by National Research Foundation of Korea (NRF) grant funded by Korea government (MIST)(2019R1A4A1028134 and 2021R1F1A1062347). Funding Information: Jung{\textquoteright}s work has been partially supported by National Research Foundation of Korea (NRF) grants funded by the Korea government(MIST) 2019R1A4A1028134 and 2021R1F1A1062347. 1Corresponding author: Department of Statistics, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, South Korea. E-mail: [email protected] Publisher Copyright: {\textcopyright} 2022. The Korean Statistical Society, and Korean International Statistical Society. All rights reserved",

year = "2022",

month = mar,

doi = "10.29220/CSAM.2022.29.2.161",

language = "English",

volume = "29",

pages = "161--176",

journal = "Communications for Statistical Applications and Methods",

issn = "2287-7843",

publisher = "Korean Statistical Society",

number = "2",

}

TY - JOUR

T1 - A review and comparison of convolution neural network models under a unified framework

AU - Park, Jimin

AU - Jung, Yoonsuh

N1 - Funding Information: Yoonsuh Jung’s work was partially supported by National Research Foundation of Korea (NRF) grant funded by Korea government (MIST)(2019R1A4A1028134 and 2021R1F1A1062347). Funding Information: Jung’s work has been partially supported by National Research Foundation of Korea (NRF) grants funded by the Korea government(MIST) 2019R1A4A1028134 and 2021R1F1A1062347. 1Corresponding author: Department of Statistics, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, South Korea. E-mail: [email protected] Publisher Copyright: © 2022. The Korean Statistical Society, and Korean International Statistical Society. All rights reserved

PY - 2022/3

Y1 - 2022/3

N2 - There has been active research in image classification using deep learning convolutional neural network (CNN) models. ImageNet large-scale visual recognition challenge (ILSVRC) (2010-2017) was one of the most important competitions that boosted the development of efficient deep learning algorithms. This paper introduces and compares six monumental models that achieved high prediction accuracy in ILSVRC. First, we provide a review of the models to illustrate their unique structure and characteristics of the models. We then compare those models under a unified framework. For this reason, additional devices that are not crucial to the structure are excluded. Four popular data sets with different characteristics are then considered to measure the prediction accuracy. By investigating the characteristics of the data sets and the models being compared, we provide some insight into the architectural features of the models.

AB - There has been active research in image classification using deep learning convolutional neural network (CNN) models. ImageNet large-scale visual recognition challenge (ILSVRC) (2010-2017) was one of the most important competitions that boosted the development of efficient deep learning algorithms. This paper introduces and compares six monumental models that achieved high prediction accuracy in ILSVRC. First, we provide a review of the models to illustrate their unique structure and characteristics of the models. We then compare those models under a unified framework. For this reason, additional devices that are not crucial to the structure are excluded. Four popular data sets with different characteristics are then considered to measure the prediction accuracy. By investigating the characteristics of the data sets and the models being compared, we provide some insight into the architectural features of the models.

KW - Classification

KW - ImageNet large-scale visual recog nition challenge (ILSVRC)

KW - convolutional neural network (CNN)

KW - image data

UR - http://www.scopus.com/inward/record.url?scp=85129427077&partnerID=8YFLogxK

U2 - 10.29220/CSAM.2022.29.2.161

DO - 10.29220/CSAM.2022.29.2.161

M3 - Article

AN - SCOPUS:85129427077

SN - 2287-7843

VL - 29

SP - 161

EP - 176

JO - Communications for Statistical Applications and Methods

JF - Communications for Statistical Applications and Methods

IS - 2

ER -

A review and comparison of convolution neural network models under a unified framework

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this