2020 39th Chinese Control Conference (CCC) 2020
DOI: 10.23919/ccc50068.2020.9189610
|View full text |Cite
|
Sign up to set email alerts
|

Convolutional Neural Network Pruning: A Survey

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
20
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 47 publications
(23 citation statements)
references
References 29 publications
0
20
0
Order By: Relevance
“…[32] treats theory and methods of quantization and discusses their merits and drawbacks while the complementary work [33] discusses frameworks and methods for executing DNNs on Field Programmable Gate Array (FPGA). DNN pruning techniques are surveyed and categorized by [34]. Recent developments in DNN architectures are described in [25], which provides an overview not only over the SOTA but also the historical developments that lead there.…”
Section: Related Surveysmentioning
confidence: 99%
“…[32] treats theory and methods of quantization and discusses their merits and drawbacks while the complementary work [33] discusses frameworks and methods for executing DNNs on Field Programmable Gate Array (FPGA). DNN pruning techniques are surveyed and categorized by [34]. Recent developments in DNN architectures are described in [25], which provides an overview not only over the SOTA but also the historical developments that lead there.…”
Section: Related Surveysmentioning
confidence: 99%
“…This technique can also be applied with quantization [229] and is discussed in Section 4. Network pruning [191,24,12,241] involves removing parameters that don't impact network accuracy. Pruning is described extensively in Section 3.…”
Section: Introductionmentioning
confidence: 99%
“…While early work focused on pruning fully trained networks [7]- [10], recent work has shown that various methods can be used to remove parameters from the network at different stages of the training process [11], [12]. The pruning schemes can be categorized according to three dimensions: pruning method, training strategy, and estimation criterion [13]. Saliency metrics or estimation criteria [13] are used to estimate which weights can be pruned from the network.…”
Section: Introductionmentioning
confidence: 99%
“…The pruning schemes can be categorized according to three dimensions: pruning method, training strategy, and estimation criterion [13]. Saliency metrics or estimation criteria [13] are used to estimate which weights can be pruned from the network. Saliency metrics are used whether pruning is incorporated into the training algorithm [14]- [21] or occurs in discrete steps which sets weights to zero [4], [9]- [12], [22]- [25].…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation