InstanceCut: From Edges to Instances with MultiCut

This work addresses the task of instance-aware semantic segmentation. Our key motivation is to design a simple method with a new modelling-paradigm, which therefore has a different trade-off between advantages and disadvantages compared to known approaches. Our approach, we term InstanceCut, represe...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) s. 7322 - 7331
Hlavní autori: Kirillov, Alexander, Levinkov, Evgeny, Andres, Bjoern, Savchynskyy, Bogdan, Rother, Carsten
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.07.2017
Predmet:
Automobiles
Image edge detection
Image segmentation
Pipelines
Proposals
Semantics
ISSN:1063-6919, 1063-6919
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract This work addresses the task of instance-aware semantic segmentation. Our key motivation is to design a simple method with a new modelling-paradigm, which therefore has a different trade-off between advantages and disadvantages compared to known approaches. Our approach, we term InstanceCut, represents the problem by two output modalities: (i) an instance-agnostic semantic segmentation and (ii) all instance-boundaries. The former is computed from a standard convolutional neural network for semantic segmentation, and the latter is derived from a new instance-aware edge detection model. To reason globally about the optimal partitioning of an image into instances, we combine these two modalities into a novel MultiCut formulation. We evaluate our approach on the challenging CityScapes dataset. Despite the conceptual simplicity of our approach, we achieve the best result among all published methods, and perform particularly well for rare object classes.
AbstractList This work addresses the task of instance-aware semantic segmentation. Our key motivation is to design a simple method with a new modelling-paradigm, which therefore has a different trade-off between advantages and disadvantages compared to known approaches. Our approach, we term InstanceCut, represents the problem by two output modalities: (i) an instance-agnostic semantic segmentation and (ii) all instance-boundaries. The former is computed from a standard convolutional neural network for semantic segmentation, and the latter is derived from a new instance-aware edge detection model. To reason globally about the optimal partitioning of an image into instances, we combine these two modalities into a novel MultiCut formulation. We evaluate our approach on the challenging CityScapes dataset. Despite the conceptual simplicity of our approach, we achieve the best result among all published methods, and perform particularly well for rare object classes.
Author Kirillov, Alexander
Levinkov, Evgeny
Andres, Bjoern
Rother, Carsten
Savchynskyy, Bogdan
Author_xml – sequence: 1
  givenname: Alexander
  surname: Kirillov
  fullname: Kirillov, Alexander
  email: Alexander.Kirillov@tu-dresden.de
  organization: Tech. Univ. Dresden, Dresden, Germany
– sequence: 2
  givenname: Evgeny
  surname: Levinkov
  fullname: Levinkov, Evgeny
  email: Levinkov@mpi-inf.mpg.de
  organization: MPI for Inf., Saarbrucken, Germany
– sequence: 3
  givenname: Bjoern
  surname: Andres
  fullname: Andres, Bjoern
  email: Andres@mpi-inf.mpg.de
  organization: MPI for Inf., Saarbrucken, Germany
– sequence: 4
  givenname: Bogdan
  surname: Savchynskyy
  fullname: Savchynskyy, Bogdan
  email: Bogdan.Savchynskyy@tu-dresden.de
  organization: Tech. Univ. Dresden, Dresden, Germany
– sequence: 5
  givenname: Carsten
  surname: Rother
  fullname: Rother, Carsten
  email: Carsten.Rother@tu-dresden.de
  organization: Tech. Univ. Dresden, Dresden, Germany
BookMark eNpNjk1Lw0AYhFepYFM9evKyfyDpu99ZbxJaLVQUUa9lk31XI20i2S3Sf29AhZ5mYJ4ZJiOTru-QkCsGBWNg59Xb03PBgZnCGHlCMqZEqUEqI0_JlIEWubbMTo78Ocli_ATgwnCYEr7qYnJdg9U-3dDl0O_owr9jpKmn_1Gk3236oA_7bWpH7IKcBbeNePmnM_K6XLxU9_n68W5V3a7zlhmV8hCcM4J7WzvGS-HR6LrWKFTTAKraYii9xhBQKSm9VE5JZccKNs54QBAzcv272yLi5mtod244bEo2fldG_ACd2Edt
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2017.774
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore
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 7331
ExternalDocumentID 8100257
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-ffaa732d9ba1283de76bb6e35cc0e5b9ef8d6effe5544d45a5459aa7eca7d0e03
IEDL.DBID RIE
ISICitedReferencesCount 174
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000418371407045&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-ffaa732d9ba1283de76bb6e35cc0e5b9ef8d6effe5544d45a5459aa7eca7d0e03
PageCount 10
ParticipantIDs ieee_primary_8100257
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 2.5152166
Snippet This work addresses the task of instance-aware semantic segmentation. Our key motivation is to design a simple method with a new modelling-paradigm, which...
SourceID ieee
SourceType Publisher
StartPage 7322
SubjectTerms Automobiles
Image edge detection
Image segmentation
Pipelines
Proposals
Semantics
Title InstanceCut: From Edges to Instances with MultiCut
URI https://ieeexplore.ieee.org/document/8100257
WOSCitedRecordID wos000418371407045&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/eLvHCXMwlV09b8IwED0B6tCJtlD1Wx46NhDixI67IlC7IFS1FRvyx1liKKkg8PtrOyF06NIp1sWRoouse7l79w7gUVlp0Y4wMgJZlErMIpV4IciciUTnIqa6GjbBZ7N8sRDzFjw1vTCIGMhnOPDLUMs3hd75VNkw93qhGW9Dm3Ne9Wo1-RTq_mSYaCoIiZ--EiqdjEZMjMRRX3M4_py_eVIXH3DP8_s1VSUElWn3f69zBv1jdx6ZN3HnHFq4voBuDSdJfVi3znSY2HCw9SB5DWhQ43hXPpPppvgiE6_yQMqCHG5tic_NktCZ67b14WM6eR-_RPXUhGjloEAZWSslp4kRSrrYQw1yphRDmmkdY6YE2twwTxZxQCI1aSYdhhLuEdSSmxhjegmddbHGKyAxV8YatEmcq9RdFboTjFIwdMAitXgNPe-V5XcljLGsHXLzt_kWTr3TK67rHXTKzQ7v4UTvy9V28xC-5g-B9p9o
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4gmugJFYxve_DowrKPduuVQCAiIQYNN9LHNOEga2Dx99vuLosHL552M90mmzbNfJ355huAR2mEQdNFT3OkXiQw9mTghCATygOVcD9URbMJNpkk8zmf1uCpqoVBxJx8hm33mufydaq2LlTWSZxeaMwO4DCOoqBbVGtVEZXQ3mUor3IIgeu_kuc6aehR3uV7hc1O72P65mhdrM0c0-9XX5XcrQwa__uhU2jt6_PItPI8Z1DD1Tk0SkBJyuO6saZdz4adrQnBKMeDCnvb7JkM1ukn6TudB5KlZDe0IS46S_LaXPtZC94H_Vlv6JV9E7ylBQOZZ4wQLAw0l8J6n1Ajo1JSDGOlfIwlR5No6ugiFkpEOoqFRVHcTkElmPbRDy-gvkpXeAnEZ1IbjSbwExnZp0R7hlFwihZaRAavoOlWZfFVSGMsygW5_tv8AMfD2et4MR5NXm7gxG1AwXy9hXq23uIdHKnvbLlZ3-c7-wP-CKKv
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=InstanceCut%3A+From+Edges+to+Instances+with+MultiCut&rft.au=Kirillov%2C+Alexander&rft.au=Levinkov%2C+Evgeny&rft.au=Andres%2C+Bjoern&rft.au=Savchynskyy%2C+Bogdan&rft.date=2017-07-01&rft.pub=IEEE&rft.issn=1063-6919&rft.eissn=1063-6919&rft.spage=7322&rft.epage=7331&rft_id=info:doi/10.1109%2FCVPR.2017.774&rft.externalDocID=8100257
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