Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/33444
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | CHEN, Siang | - |
dc.contributor.author | Huang, Kai | - |
dc.contributor.author | Xiong, Dongliang | - |
dc.contributor.author | LI, Bowen | - |
dc.contributor.author | CLAESEN, Luc | - |
dc.date.accessioned | 2021-02-12T13:09:11Z | - |
dc.date.available | 2021-02-12T13:09:11Z | - |
dc.date.issued | 2020 | - |
dc.date.submitted | 2021-02-12T11:55:58Z | - |
dc.identifier.citation | Lecture notes in computer science, 12397 , p. 3 -14 | - |
dc.identifier.isbn | 978-3-030-61615-1 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/1942/33444 | - |
dc.description.abstract | Pruning residual neural networks is a challenging task due to the constraints induced by cross layer connections. Many existing approaches assign channels connected by skip-connections to the same group and prune them simultaneously, limiting the pruning ratio on those troublesome filters. Instead, we propose a Fine-grained Channel Pruning (FCP) method that allows any channels to be pruned independently. To avoid the misalignment problem between convolution and skip connection , we always keep the residual addition operations alive. Thus we can obtain a novel efficient residual architecture by removing any unimportant channels without the alignment constraint. Besides classification, We further apply FCP on residual models for image super-resolution, which is a low-level vision task. Extensive experimental results show that FCP can achieve better performance than other state-of-the-art methods in terms of parameter and computation cost. Notably, on CIFAR-10, FCP reduces more than 78% FLOPs on ResNet-56 with no accuracy drop. Moreover, it achieves more than 48% FLOPs reduction on MSR-ResNet with negligible performance degradation. | - |
dc.language.iso | en | - |
dc.publisher | SPRINGER INTERNATIONAL PUBLISHING AG | - |
dc.subject.other | Channel pruning | - |
dc.subject.other | Residual neural network | - |
dc.subject.other | Efficient network structure | - |
dc.title | Fine-Grained Channel Pruning for Deep Residual Neural Networks | - |
dc.type | Proceedings Paper | - |
local.bibliographicCitation.authors | Farkaš, Igor | - |
local.bibliographicCitation.authors | Masulli, Paolo | - |
local.bibliographicCitation.authors | Wermter, Stefan | - |
local.bibliographicCitation.conferencename | Artificial Neural Networks and Machine Learning – ICANN 2020 | - |
local.bibliographicCitation.conferenceplace | Bratislava, Slovakia | - |
dc.identifier.epage | 14 | - |
dc.identifier.spage | 3 | - |
dc.identifier.volume | 12397 | - |
local.bibliographicCitation.jcat | C1 | - |
local.publisher.place | GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND | - |
local.type.refereed | Refereed | - |
local.type.specified | Proceedings Paper | - |
local.type.programme | VSC | - |
dc.identifier.doi | 10.1007/978-3-030-61616-8_1 | - |
dc.identifier.isi | 000713797800001 | - |
local.provider.type | CrossRef | - |
local.bibliographicCitation.btitle | Artificial Neural Networks and Machine Learning – ICANN 2020 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15–18, 2020, Proceedings, Part II | - |
local.uhasselt.uhpub | yes | - |
local.uhasselt.international | yes | - |
item.contributor | CHEN, Siang | - |
item.contributor | Huang, Kai | - |
item.contributor | Xiong, Dongliang | - |
item.contributor | LI, Bowen | - |
item.contributor | CLAESEN, Luc | - |
item.validation | ecoom 2022 | - |
item.fullcitation | CHEN, Siang; Huang, Kai; Xiong, Dongliang; LI, Bowen & CLAESEN, Luc (2020) Fine-Grained Channel Pruning for Deep Residual Neural Networks. In: Lecture notes in computer science, 12397 , p. 3 -14. | - |
item.accessRights | Open Access | - |
item.fulltext | With Fulltext | - |
crisitem.journal.issn | 0302-9743 | - |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Fine-grained Channel Pruning for Deep Residual Neural Networks.pdf | Peer-reviewed author version | 494.04 kB | Adobe PDF | View/Open |
Fine-Grained Channel Pruning for Deep Residual Neural Networks.pdf Restricted Access | Published version | 695.06 kB | Adobe PDF | View/Open Request a copy |
WEB OF SCIENCETM
Citations
1
checked on Apr 23, 2024
Page view(s)
56
checked on Sep 5, 2022
Download(s)
54
checked on Sep 5, 2022
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.