Densely Connected Convolutional Networks

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional N...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) s. 2261 - 2269
Hlavní autoři: Huang, Gao, Liu, Zhuang, Van Der Maaten, Laurens, Weinberger, Kilian Q.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.07.2017
Témata:
Convolution
Convolutional codes
Network architecture
Neural networks
Road transportation
Training
ISSN:1063-6919, 1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections-one between each layer and its subsequent layer-our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less memory and computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet.
AbstractList Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections-one between each layer and its subsequent layer-our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less memory and computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet.
Author Huang, Gao
Liu, Zhuang
Weinberger, Kilian Q.
Van Der Maaten, Laurens
Author_xml – sequence: 1
  givenname: Gao
  surname: Huang
  fullname: Huang, Gao
  email: gh349@cornell.edu
  organization: Cornell University
– sequence: 2
  givenname: Zhuang
  surname: Liu
  fullname: Liu, Zhuang
  email: liuzhuang13@mails.tsinghua.edu.cn
  organization: Tsinghua University
– sequence: 3
  givenname: Laurens
  surname: Van Der Maaten
  fullname: Van Der Maaten, Laurens
  email: lvdmaaten@fb.com
  organization: Facebook AI Research
– sequence: 4
  givenname: Kilian Q.
  surname: Weinberger
  fullname: Weinberger, Kilian Q.
  email: kqw4@cornell.edu
  organization: Cornell University
BookMark eNpNzDtPwzAUQGGDikRTGJlYOrIk3Ou3RxSeUgUIAWvl2jdSINgoDqD-e4RgYDrfdCo2SzkRY0cIDSK40_b5_qHhgKbhUuywCpWwGqQycpfNEbSotUM3--d9VpXyAsCF4TBnJ-eUCg3bZZtTojBR_NFnHj6mPic_LG9p-srjazlge50fCh3-dcGeLi8e2-t6dXd1056t6h6NmuqIFkKIESlaHXUQ1qoAmrTlkryWijZOoKBOOmclGWU7qTuzwY4L7wyJBTv-_fZEtH4f-zc_btcWnDNci2-bp0NJ
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2017.243
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
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
Computer Science
EISBN 1538604574
9781538604571
EISSN 1063-6919
EndPage 2269
ExternalDocumentID 8099726
Genre orig-research
GroupedDBID 23M
29F
29O
6IE
6IH
6IK
ABDPE
ACGFS
ALMA_UNASSIGNED_HOLDINGS
CBEJK
IPLJI
M43
RIE
RIO
RNS
ID FETCH-LOGICAL-i175t-d180ccdd1ed86d6c3885c06e6824ea645eb9313ef49984e758f46f7b1f23a97e3
IEDL.DBID RIE
ISICitedReferencesCount 27620
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000418371402035&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1063-6919
IngestDate Wed Aug 27 06:13:56 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i175t-d180ccdd1ed86d6c3885c06e6824ea645eb9313ef49984e758f46f7b1f23a97e3
PageCount 9
ParticipantIDs ieee_primary_8099726
PublicationCentury 2000
PublicationDate 2017-July
PublicationDateYYYYMMDD 2017-07-01
PublicationDate_xml – month: 07
  year: 2017
  text: 2017-July
PublicationDecade 2010
PublicationTitle 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
PublicationTitleAbbrev CVPR
PublicationYear 2017
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0023720
ssj0003211698
Score 2.630527
Snippet Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections...
SourceID ieee
SourceType Publisher
StartPage 2261
SubjectTerms Convolution
Convolutional codes
Network architecture
Neural networks
Road transportation
Training
Title Densely Connected Convolutional Networks
URI https://ieeexplore.ieee.org/document/8099726
WOSCitedRecordID wos000418371402035&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/eLvHCXMwlV1LSwMxEB5a8eCpaiu-2YMHD6btbrJ5nKvFg5QiKr2VbDKBgrTSF_jvTbLbrQcv3sKcwkzCvL5vBuAuc-gdibCEaa0JK5wgSlhDlBMoipx5JxXnzL6I0UhOJmrcgIeaC4OIEXyG3XCMvXy7MJtQKuvJSPPkTWgKIUquVl1PoT6T4aruIGRh-0rsdHJKuErVfr5mb_Axfg2gLtHNAlnn11aV6FSGrf9d5xg6e3ZeMq79zgk0cH4KrSqcTKrPuvKi3caGnawN948YGOjfScS3GB9thtO2en76MxmVqPBVB96HT2-DZ1LtSiAzHwCsiU1l3xhrU7SSW26olLnpc-QyY6g5y7FQNKXofIYjGfoswTHuRJG6jGolkJ7BwXwxx3NIvO2stjktGCJLC-nNVoh-7phTzipLL6AddDH9KsdhTCs1XP4tvoKjoOoS4XoNB-vlBm_g0GzXs9XyNtrwB_8Mmro
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4gmugJFYxv9-DBg0V22-3jjBKMuCEGDTeyu50mJAYMr8R_b9tdwIMXb82cmpk28_q-GYDbyKB1JEITlqYpYZkRRAmdE2UEiixm1kn5ObM9kSRyOFT9CtxvuDCI6MFn2HRH38vX03zpSmUP0tM8-Q7sxoxFYcHW2lRUqM1luNr0ECK3f8X3OjklXIVqO2Hzof3Rf3OwLtGMHF3n114V71Y6tf9d6BAaW35e0N94niOo4OQYamVAGZTfdW5F650Na1kd7h7RcdC_A49wyW286U6r8gGmn0FS4MLnDXjvPA3aXVJuSyBjGwIsiA5lK8-1DlFLrnlOpYzzFkcuI4YpZzFmioYUjc1xJEObJxjGjchCE9FUCaQnUJ1MJ3gKgbWeTnVMM4bIwkxaw2WiFRtmlNFK0zOoO12MvoqBGKNSDed_i29gvzt47Y16z8nLBRw4tRd410uoLmZLvIK9fLUYz2fX3p4_PxWeAQ
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%3Ajournal&rft.genre=proceeding&rft.title=2017+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29&rft.atitle=Densely+Connected+Convolutional+Networks&rft.au=Huang%2C+Gao&rft.au=Liu%2C+Zhuang&rft.au=Van+Der+Maaten%2C+Laurens&rft.au=Weinberger%2C+Kilian+Q.&rft.date=2017-07-01&rft.pub=IEEE&rft.issn=1063-6919&rft.eissn=1063-6919&rft.spage=2261&rft.epage=2269&rft_id=info:doi/10.1109%2FCVPR.2017.243&rft.externalDocID=8099726
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-6919&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-6919&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-6919&client=summon