DenseASPP for Semantic Segmentation in Street Scenes

Semantic image segmentation is a basic street scene understanding task in autonomous driving, where each pixel in a high resolution image is categorized into a set of semantic labels. Unlike other scenarios, objects in autonomous driving scene exhibit very large scale changes, which poses great chal...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition S. 3684 - 3692
Hauptverfasser: Yang, Maoke, Yu, Kun, Zhang, Chi, Li, Zhiwei, Yang, Kuiyuan
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2018
Schlagworte:
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Semantic image segmentation is a basic street scene understanding task in autonomous driving, where each pixel in a high resolution image is categorized into a set of semantic labels. Unlike other scenarios, objects in autonomous driving scene exhibit very large scale changes, which poses great challenges for high-level feature representation in a sense that multi-scale information must be correctly encoded. To remedy this problem, atrous convolution[14]was introduced to generate features with larger receptive fields without sacrificing spatial resolution. Built upon atrous convolution, Atrous Spatial Pyramid Pooling (ASPP)[2] was proposed to concatenate multiple atrous-convolved features using different dilation rates into a final feature representation. Although ASPP is able to generate multi-scale features, we argue the feature resolution in the scale-axis is not dense enough for the autonomous driving scenario. To this end, we propose Densely connected Atrous Spatial Pyramid Pooling (DenseASPP), which connects a set of atrous convolutional layers in a dense way, such that it generates multi-scale features that not only cover a larger scale range, but also cover that scale range densely, without significantly increasing the model size. We evaluate DenseASPP on the street scene benchmark Cityscapes[4] and achieve state-of-the-art performance.
AbstractList Semantic image segmentation is a basic street scene understanding task in autonomous driving, where each pixel in a high resolution image is categorized into a set of semantic labels. Unlike other scenarios, objects in autonomous driving scene exhibit very large scale changes, which poses great challenges for high-level feature representation in a sense that multi-scale information must be correctly encoded. To remedy this problem, atrous convolution[14]was introduced to generate features with larger receptive fields without sacrificing spatial resolution. Built upon atrous convolution, Atrous Spatial Pyramid Pooling (ASPP)[2] was proposed to concatenate multiple atrous-convolved features using different dilation rates into a final feature representation. Although ASPP is able to generate multi-scale features, we argue the feature resolution in the scale-axis is not dense enough for the autonomous driving scenario. To this end, we propose Densely connected Atrous Spatial Pyramid Pooling (DenseASPP), which connects a set of atrous convolutional layers in a dense way, such that it generates multi-scale features that not only cover a larger scale range, but also cover that scale range densely, without significantly increasing the model size. We evaluate DenseASPP on the street scene benchmark Cityscapes[4] and achieve state-of-the-art performance.
Author Li, Zhiwei
Yu, Kun
Zhang, Chi
Yang, Kuiyuan
Yang, Maoke
Author_xml – sequence: 1
  givenname: Maoke
  surname: Yang
  fullname: Yang, Maoke
– sequence: 2
  givenname: Kun
  surname: Yu
  fullname: Yu, Kun
– sequence: 3
  givenname: Chi
  surname: Zhang
  fullname: Zhang, Chi
– sequence: 4
  givenname: Zhiwei
  surname: Li
  fullname: Li, Zhiwei
– sequence: 5
  givenname: Kuiyuan
  surname: Yang
  fullname: Yang, Kuiyuan
BookMark eNotzL1KxEAUQOFRFFzX1BY2eYHEe-f3TrmsrgoLBrPYLuPkRkbMRJI0vr2CVuerzqU4y2NmIa4RakTwt9vX5qWWgFQDKKITUXhHaBRZqyX4U7FCsKqyHv2FKOb5AwCkJUXarIS-4zzzpm2ash-nsuUh5CXFX7wPnJewpDGXKZftMjEvZRs583wlzvvwOXPx37U47O4P28dq__zwtN3sq4TOLFWHHbAF7ajvpUQnwVEwpgcHGCgSeYzRhjfWNqB23jrvuI-aQXYcvVqLm79tYubj15SGMH0fyTjSZNUPJe1F-Q
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2018.00388
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 Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 9781538664209
1538664208
EISSN 1063-6919
EndPage 3692
ExternalDocumentID 8578486
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-d1d0e60478ff22172078a55f0701a8c8891cc6abe46a14796797efc4e02dec93
IEDL.DBID RIE
ISICitedReferencesCount 1315
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000457843603086&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-d1d0e60478ff22172078a55f0701a8c8891cc6abe46a14796797efc4e02dec93
PageCount 9
ParticipantIDs ieee_primary_8578486
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 2.64942
Snippet Semantic image segmentation is a basic street scene understanding task in autonomous driving, where each pixel in a high resolution image is categorized into a...
SourceID ieee
SourceType Publisher
StartPage 3684
SubjectTerms Autonomous vehicles
Convolution
Image resolution
Image segmentation
Kernel
Neurons
Semantics
Title DenseASPP for Semantic Segmentation in Street Scenes
URI https://ieeexplore.ieee.org/document/8578486
WOSCitedRecordID wos000457843603086&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/eLvHCXMwlV07T8MwED61FQNTgRbxVgZGQpPY8WNEhYoBVRGtqm6Va19QhqaoD34_5yQqDCxstiVL9vlx990T4D5VaFiqCZugNARQHIYkhcjQEgwTeeR4Uin0Z29yPFbzuc5a8HCIhUHEyvkMH32zsuW7td17VdlA0fXiSrShLaWsY7UO-pREKKYaC5nvM0I2Qqsmm08c6cFwlr17Xy7vPMl8pZVf5VQqbjLq_m8dJ9D_CcsLsgPDOYUWlmfQbeTIoHml2x7wZ8Km-DTJsoBE0mCCKyJfYanxsWpCjcqgKIPaIk0T_X_Xh-noZTp8DZvqCGFBLH8XuthFKHxynTxPfJkpYvYmTXN6w7FRVikdWyvMErkwMZdaSC0xtxyjxKHV7Bw65brECwgQmXOWsdSklqtYKpGzpTCcusIn17mEnqfB4rPOf7Fotn_19_A1HHsi1-5UN9DZbfZ4C0f2a1dsN3fVoX0DIz6VRA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED6VggRTgRbxJgMjgSZ2HHtEhaqIUkW0qrpVrn1BGZqiPvj9nJOoMLCw2ZYs2efH3XdPgNtIomaRImyCsSaAYtEnKST2DcEwkbYtDwuF_rgfDwZyMlFJDe62sTCIWDif4b1rFrZ8uzAbpyp7kHS9uBQ7sBtxHgZltNZWoxIKyWRlI3N9RthGKFnl8wna6qEzTt6dN5dzn2Su1sqvgioFP-k2_reSQ2j9BOZ5yZblHEEN82NoVJKkV73TVRP4E6FTfBwmiUdCqTfEOREwM9T4mFfBRrmX5V5pk6aJ7sdrwaj7POr0_Ko-gp8R01_7NrBtFC69TpqGrtAUsXsdRSm94kBLI6UKjBF6hlzogMdKxCrG1HBshxaNYidQzxc5noKHyKw1jEU6MlwGsRQpmwnNqStcep0zaDoaTD_LDBjTavvnfw_fwH5v9Naf9l8Grxdw4AheOlddQn293OAV7JmvdbZaXhcH-A0ar5iL
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=DenseASPP+for+Semantic+Segmentation+in+Street+Scenes&rft.au=Yang%2C+Maoke&rft.au=Yu%2C+Kun&rft.au=Zhang%2C+Chi&rft.au=Li%2C+Zhiwei&rft.date=2018-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=3684&rft.epage=3692&rft_id=info:doi/10.1109%2FCVPR.2018.00388&rft.externalDocID=8578486