Convolutional Neural Network Pruning: A Survey

Sheng Xu; Anran Huang; Lei Chen; Baochang Zhang

doi:10.23919/CCC50068.2020.9189610

Convolutional Neural Network Pruning: A Survey

Sheng Xu, Anran Huang, Lei Chen^*, Baochang Zhang

^*Corresponding author for this work

Beihang University

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

36 Citations (Scopus)

Abstract

Deep convolutional neural networks have enabled remarkable progress over the last years on a variety of visual tasks, such as image recognition, speech recognition, and machine translation. These tasks contribute many to machine intelligence. However, developments of deep convolutional neural networks to a machine terminal remains challenging due to massive number of parameters and float operations that a typical model contains. Therefore, there is growing interest in convolutional neural network pruning. Existing work in this field of research can be categorized according to three dimensions: pruning method, training strategy, estimation criterion.

Original language	English
Title of host publication	Proceedings of the 39th Chinese Control Conference, CCC 2020
Editors	Jun Fu, Jian Sun
Publisher	IEEE Computer Society
Pages	7458-7463
Number of pages	6
ISBN (Electronic)	9789881563903
DOIs	https://doi.org/10.23919/CCC50068.2020.9189610
Publication status	Published - Jul 2020
Externally published	Yes
Event	39th Chinese Control Conference, CCC 2020 - Shenyang, China Duration: 27 Jul 2020 → 29 Jul 2020

Publication series

Name	Chinese Control Conference, CCC
Volume	2020-July
ISSN (Print)	1934-1768
ISSN (Electronic)	2161-2927

Conference

Conference	39th Chinese Control Conference, CCC 2020
Country/Territory	China
City	Shenyang
Period	27/07/20 → 29/07/20

Keywords

convolutional neural networks
estimation criterion
machine intelligence
pruning method
training strategy

Access to Document

10.23919/CCC50068.2020.9189610

Cite this

@inproceedings{58710c7a3ee34b819105fb80704de220,

title = "Convolutional Neural Network Pruning: A Survey",

abstract = "Deep convolutional neural networks have enabled remarkable progress over the last years on a variety of visual tasks, such as image recognition, speech recognition, and machine translation. These tasks contribute many to machine intelligence. However, developments of deep convolutional neural networks to a machine terminal remains challenging due to massive number of parameters and float operations that a typical model contains. Therefore, there is growing interest in convolutional neural network pruning. Existing work in this field of research can be categorized according to three dimensions: pruning method, training strategy, estimation criterion.",

keywords = "convolutional neural networks, estimation criterion, machine intelligence, pruning method, training strategy",

author = "Sheng Xu and Anran Huang and Lei Chen and Baochang Zhang",

note = "Publisher Copyright: {\textcopyright} 2020 Technical Committee on Control Theory, Chinese Association of Automation.; 39th Chinese Control Conference, CCC 2020 ; Conference date: 27-07-2020 Through 29-07-2020",

year = "2020",

month = jul,

doi = "10.23919/CCC50068.2020.9189610",

language = "English",

series = "Chinese Control Conference, CCC",

publisher = "IEEE Computer Society",

pages = "7458--7463",

editor = "Jun Fu and Jian Sun",

booktitle = "Proceedings of the 39th Chinese Control Conference, CCC 2020",

address = "United States",

}

Xu, S, Huang, A, Chen, L & Zhang, B 2020, Convolutional Neural Network Pruning: A Survey. in J Fu & J Sun (eds), Proceedings of the 39th Chinese Control Conference, CCC 2020., 9189610, Chinese Control Conference, CCC, vol. 2020-July, IEEE Computer Society, pp. 7458-7463, 39th Chinese Control Conference, CCC 2020, Shenyang, China, 27/07/20. https://doi.org/10.23919/CCC50068.2020.9189610

Convolutional Neural Network Pruning: A Survey. / Xu, Sheng; Huang, Anran; Chen, Lei et al.
Proceedings of the 39th Chinese Control Conference, CCC 2020. ed. / Jun Fu; Jian Sun. IEEE Computer Society, 2020. p. 7458-7463 9189610 (Chinese Control Conference, CCC; Vol. 2020-July).

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

TY - GEN

T1 - Convolutional Neural Network Pruning

T2 - 39th Chinese Control Conference, CCC 2020

AU - Xu, Sheng

AU - Huang, Anran

AU - Chen, Lei

AU - Zhang, Baochang

PY - 2020/7

Y1 - 2020/7

N2 - Deep convolutional neural networks have enabled remarkable progress over the last years on a variety of visual tasks, such as image recognition, speech recognition, and machine translation. These tasks contribute many to machine intelligence. However, developments of deep convolutional neural networks to a machine terminal remains challenging due to massive number of parameters and float operations that a typical model contains. Therefore, there is growing interest in convolutional neural network pruning. Existing work in this field of research can be categorized according to three dimensions: pruning method, training strategy, estimation criterion.

AB - Deep convolutional neural networks have enabled remarkable progress over the last years on a variety of visual tasks, such as image recognition, speech recognition, and machine translation. These tasks contribute many to machine intelligence. However, developments of deep convolutional neural networks to a machine terminal remains challenging due to massive number of parameters and float operations that a typical model contains. Therefore, there is growing interest in convolutional neural network pruning. Existing work in this field of research can be categorized according to three dimensions: pruning method, training strategy, estimation criterion.

KW - convolutional neural networks

KW - estimation criterion

KW - machine intelligence

KW - pruning method

KW - training strategy

UR - http://www.scopus.com/inward/record.url?scp=85091395311&partnerID=8YFLogxK

U2 - 10.23919/CCC50068.2020.9189610

DO - 10.23919/CCC50068.2020.9189610

M3 - Conference contribution

AN - SCOPUS:85091395311

T3 - Chinese Control Conference, CCC

SP - 7458

EP - 7463

BT - Proceedings of the 39th Chinese Control Conference, CCC 2020

A2 - Fu, Jun

A2 - Sun, Jian

PB - IEEE Computer Society

Y2 - 27 July 2020 through 29 July 2020

ER -

Convolutional Neural Network Pruning: A Survey

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this