ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly red...
Saved in:
| Published in: | 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 6848 - 6856 |
|---|---|
| Main Authors: | , , , |
| Format: | Conference Proceeding |
| Language: | English |
| Published: |
IEEE
01.06.2018
|
| Subjects: | |
| ISSN: | 1063-6919 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly reduce computation cost while maintaining accuracy. Experiments on ImageNet classification and MS COCO object detection demonstrate the superior performance of ShuffleNet over other structures, e.g. lower top-1 error (absolute 7.8%) than recent MobileNet [12] on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves ~13Ã- actual speedup over AlexNet while maintaining comparable accuracy. |
|---|---|
| AbstractList | We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly reduce computation cost while maintaining accuracy. Experiments on ImageNet classification and MS COCO object detection demonstrate the superior performance of ShuffleNet over other structures, e.g. lower top-1 error (absolute 7.8%) than recent MobileNet [12] on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves ~13Ã- actual speedup over AlexNet while maintaining comparable accuracy. |
| Author | Zhou, Xinyu Lin, Mengxiao Zhang, Xiangyu Sun, Jian |
| Author_xml | – sequence: 1 givenname: Xiangyu surname: Zhang fullname: Zhang, Xiangyu – sequence: 2 givenname: Xinyu surname: Zhou fullname: Zhou, Xinyu – sequence: 3 givenname: Mengxiao surname: Lin fullname: Lin, Mengxiao – sequence: 4 givenname: Jian surname: Sun fullname: Sun, Jian |
| BookMark | eNotjMlOwzAUAA0CiVJy5sDFP5DiFzvPNrcqlEUqBZWKa5XlWRjSGGVp6d9TAafRzGHO2UkTGmLsEsQEQNjr7O1lOUkEmIkQGvCIRVYbSKVBVImwx2wEAmWMFuwZi7ruQwiRoJFGpSO2fH0fnKtpQf0NnzZ89t23tKF6z2fO-dJT0_MsNNtQD70PTV7zBQ3tL_pdaD-5Cy1_CoWvid_S1pfUXbBTl9cdRf8cs9XdbJU9xPPn-8dsOo896LSPpUxBS0ykroRKAQVUlXYWS9QFoUKTFzZBkLmkQ68U2fLguZNCGbSFHLOrv60novVX6zd5u1-bVBsDSv4Av1NQ8A |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/CVPR.2018.00716 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library (IEL) (UW System Shared) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences |
| EISBN | 9781538664209 1538664208 |
| EISSN | 1063-6919 |
| EndPage | 6856 |
| ExternalDocumentID | 8578814 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IH 6IL 6IN AAWTH ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP OCL RIE RIL RIO |
| ID | FETCH-LOGICAL-i175t-3351736237d0451601dd7f96c67be6468ab92613a3ed7fd4e9c926af304869b3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 6507 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000457843607001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Aug 27 02:52:16 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i175t-3351736237d0451601dd7f96c67be6468ab92613a3ed7fd4e9c926af304869b3 |
| PageCount | 9 |
| ParticipantIDs | ieee_primary_8578814 |
| PublicationCentury | 2000 |
| PublicationDate | 2018-Jun |
| PublicationDateYYYYMMDD | 2018-06-01 |
| PublicationDate_xml | – month: 06 year: 2018 text: 2018-Jun |
| PublicationDecade | 2010 |
| PublicationTitle | 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition |
| PublicationTitleAbbrev | CVPR |
| PublicationYear | 2018 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0002683845 ssj0003211698 |
| Score | 2.6476233 |
| Snippet | We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 6848 |
| SubjectTerms | Complexity theory Computational modeling Computer architecture Convolution Mobile handsets Neural networks Task analysis |
| Title | ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices |
| URI | https://ieeexplore.ieee.org/document/8578814 |
| WOSCitedRecordID | wos000457843607001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4g8eAJFYzv9ODRlV1a-vBmEOJBCUFiuJHtK5IQMLAQ_fdOywY9ePG02x6aTdvtzDf95huAG4s2nTJjkqzVyhGgqDTRWmeJVSbV3jI0MTFR-Fn0-3I8VoMK3O5yYZxzkXzm7sJrvMu3C7MOobKmbAfxc7YHe0KIba7WLp7S4pLK8oYstCkiG65kqeaTparZeRsMA5crkCdFqG_-q5xKtCa92v--4xAaP2l5ZLAzOEdQcfNjqJV-JCn_0lUdhq_va-9nru-Ke_IwJ93PIkQBZ1-kGwUjcHCCQ27KXZfPSJDoiI_ICSfoyJKXhcYDgzy6eJQ0YNTrjjpPSVk7IZmiQ1AklLYzgcaJChsUZBB2WSu84oYL7TjjMtcKwRPNqcN-y5wy2M49DRJ8StMTqM4Xc3cKxCKgSNENNLLtmfRK6txK7hnlGl0Dyc6gHmZo8rFVx5iUk3P-d_cFHIQl2JKtLqFaLNfuCvbNppiultdxSb8BEE2gWQ |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4QTfSECsbf9uDRybZ2XevNIAQjLASJ4UbWtY0kZBgYRP97X8uCHrx42tpDs7Rd3_tev_c9hG4V2HRCs8wLwjAFgCJ8T0oZeEpkvjSKgolxicK9OEn4eCwGFXS3zYXRWjvymb63r-4uX82zlQ2VNXlkxc_pDtqNKA2DTbbWNqISMk54eUdm2wSwDRO81PMJfNFsvQ2Gls1l6ZOxrXD-q6CKsyed2v--5BA1fhLz8GBrco5QRefHqFZ6krj8T5d1NHx9Xxkz04kuHvBjjtufhY0Dzr5w20lGwOAYhlyX-y6dYSvS4R6OFY7BlcX9uYQjAz9pd5g00KjTHrW6Xlk9wZuCS1B4hERBDOaJxMpqyADwUio2gmUslppRxlMpAD6RlGjoV1SLDNqpIVaET0hygqr5PNenCCuAFD44ghmPDOVGcJkqzgwlTIJzwOkZqtsZmnxs9DEm5eSc_919g_a7o35v0ntOXi7QgV2ODfXqElWLxUpfob1sXUyXi2u3vN-Y1qOg |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2018+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.atitle=ShuffleNet%3A+An+Extremely+Efficient+Convolutional+Neural+Network+for+Mobile+Devices&rft.au=Zhang%2C+Xiangyu&rft.au=Zhou%2C+Xinyu&rft.au=Lin%2C+Mengxiao&rft.au=Sun%2C+Jian&rft.date=2018-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=6848&rft.epage=6856&rft_id=info:doi/10.1109%2FCVPR.2018.00716&rft.externalDocID=8578814 |