Pyramid Scene Parsing Network

Scene parsing is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of global context information by different-region-based context aggregation through our pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet)....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) S. 6230 - 6239
Hauptverfasser: Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.07.2017
Schlagworte:
Automobiles
Convolution
Feature extraction
Image segmentation
Neural networks
Semantics
ISSN:1063-6919, 1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Scene parsing is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of global context information by different-region-based context aggregation through our pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet). Our global prior representation is effective to produce good quality results on the scene parsing task, while PSPNet provides a superior framework for pixel-level prediction. The proposed approach achieves state-of-the-art performance on various datasets. It came first in ImageNet scene parsing challenge 2016, PASCAL VOC 2012 benchmark and Cityscapes benchmark. A single PSPNet yields the new record of mIoU accuracy 85.4% on PASCAL VOC 2012 and accuracy 80.2% on Cityscapes.
AbstractList Scene parsing is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of global context information by different-region-based context aggregation through our pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet). Our global prior representation is effective to produce good quality results on the scene parsing task, while PSPNet provides a superior framework for pixel-level prediction. The proposed approach achieves state-of-the-art performance on various datasets. It came first in ImageNet scene parsing challenge 2016, PASCAL VOC 2012 benchmark and Cityscapes benchmark. A single PSPNet yields the new record of mIoU accuracy 85.4% on PASCAL VOC 2012 and accuracy 80.2% on Cityscapes.
Author Hengshuang Zhao
Xiaojuan Qi
Jiaya Jia
Jianping Shi
Xiaogang Wang
Author_xml – sequence: 1
  surname: Hengshuang Zhao
  fullname: Hengshuang Zhao
  email: hszhao@cse.cuhk.edu.hk
– sequence: 2
  surname: Jianping Shi
  fullname: Jianping Shi
  email: shijianping@sensetime.com
– sequence: 3
  surname: Xiaojuan Qi
  fullname: Xiaojuan Qi
  email: xjqi@cse.cuhk.edu.hk
– sequence: 4
  surname: Xiaogang Wang
  fullname: Xiaogang Wang
  email: xgwang@ee.cuhk.edu.hk
– sequence: 5
  surname: Jiaya Jia
  fullname: Jiaya Jia
  email: leojia@cse.cuhk.edu.hk
BookMark eNpNTk1Lw0AUfEoFm-rRkwj5A4nv7fceJVgtFA1-Xcu6eZGoTWVTkP57I3ooAzMDMwyTwaTf9AxwRlgSob-sXuqHUiDZ0hg8gIy0dAaVtuoQpoRGFsaTn-z5Y8iG4R1RSCtwChf1LoV11-SPkXvO65CGrn_L73j7vUkfJ3DUhs-BT_91Bs_z66fqtlje3yyqq2XRkdXbojEjVHTWea1UYDbOopdsBSO1ZF-ltyONCUWjqWmobX8bwsVg4vh5Bud_ux0zr75Stw5pt3KESErKH8FCPgw
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2017.660
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
Computer Science
EISBN 1538604574
9781538604571
EISSN 1063-6919
EndPage 6239
ExternalDocumentID 8100143
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-d6d6d4c8789544aee687093e72e01f17b3977b34ae1c651dd1ff870928ca6c153
IEDL.DBID RIE
ISICitedReferencesCount 10989
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000418371406035&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 02:33:41 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i175t-d6d6d4c8789544aee687093e72e01f17b3977b34ae1c651dd1ff870928ca6c153
PageCount 10
ParticipantIDs ieee_primary_8100143
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 2.6283731
Snippet Scene parsing is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of global context information by...
SourceID ieee
SourceType Publisher
StartPage 6230
SubjectTerms Automobiles
Convolution
Feature extraction
Image segmentation
Neural networks
Semantics
Title Pyramid Scene Parsing Network
URI https://ieeexplore.ieee.org/document/8100143
WOSCitedRecordID wos000418371406035&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/eLvHCXMwlV07T8MwED61FQNTgRbxKsrAiNs87XiuqJiiCAHqVjn2WepAi_pA4t9zdtKUgQVlsS4eHEf2fff8AB7I7DEE2izDJCMDRfCQVSnXzKgqM0oTQOXWk02Iosjnc1l24LGthUFEn3yGYzf0sXyz1nvnKpvkrmFQmnShK4Soa7Vaf0pClgyXbQQhduwrPtLJE8ZlJI_9NSfT9_LFJXWJse9M-YtVxSuVWf9_yzmD4bE6LyhbvXMOHVxdQL-Bk0FzWLckOjA2HGQDGJXfG_WxdLPojgtK5V0FQVHngg_hbfb0On1mDUECW5LW3zHD6Ul1LnKZpalC5HT6ZIIixjCykagcuqsSehNpnkXGRNa6GXGuFdd0111Cb7Ve4RUEVeq4-UKZ89CkaGOlCLoRODKobGzi7BoGbgMWn3UPjEXz7Td_i2_h1O1vndZ6B73dZo8jONFfu-V2c-9_3A-F6pRQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED6VggRTgRbxKmRgxG0ejpPMFaiIEkWooG6VY1-kDrSoDyT-PWcnTRlYUJbo4iG5yL7vnh_AHbk9mkBbwTAIyUGJhMtyLhTTMg-1VARQRWHJJqI0jSeTJGvAfd0Lg4i2-Ax75tbm8vVCbUyorB-bgUE82IP9kHPfK7u16ohKQL6MSOocgm_4V2yuUwRMJF6ym7DZH7xnr6asK-rZ2ZS_eFWsWXls_e-FjqGz689zstrynEAD56fQqgClU23XFYm2nA1bWRu62fdSfszMKjrlnEzaYIGTltXgHXh7fBgPhqyiSGAzsvtrpgVdXMVRnJBKJKKg_ZcEGPnoeoUX5Qbf5QE98ZQIPa29ojAr_FhJoei0O4PmfDHHc3Bybtj53CQWruZY-FISeCN4pFEWvvbDC2gbBUw_yykY0-rbL_8W38LhcPwymo6e0ucrODK6Lotcr6G5Xm6wCwfqaz1bLW_sT_wBdD2Xlw
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=Pyramid+Scene+Parsing+Network&rft.au=Hengshuang+Zhao&rft.au=Jianping+Shi&rft.au=Xiaojuan+Qi&rft.au=Xiaogang+Wang&rft.date=2017-07-01&rft.pub=IEEE&rft.issn=1063-6919&rft.eissn=1063-6919&rft.spage=6230&rft.epage=6239&rft_id=info:doi/10.1109%2FCVPR.2017.660&rft.externalDocID=8100143
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