Learning to Adapt Structured Output Space for Semantic Segmentation

Convolutional neural network-based approaches for semantic segmentation rely on supervision with pixel-level ground truth, but may not generalize well to unseen image domains. As the labeling process is tedious and labor intensive, developing algorithms that can adapt source ground truth labels to t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition S. 7472 - 7481
Hauptverfasser: Tsai, Yi-Hsuan, Hung, Wei-Chih, Schulter, Samuel, Sohn, Kihyuk, Yang, Ming-Hsuan, Chandraker, Manmohan
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2018
Schlagworte:
Adaptation models
Image segmentation
Layout
Prediction algorithms
Semantics
Task analysis
Training
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Convolutional neural network-based approaches for semantic segmentation rely on supervision with pixel-level ground truth, but may not generalize well to unseen image domains. As the labeling process is tedious and labor intensive, developing algorithms that can adapt source ground truth labels to the target domain is of great interest. In this paper, we propose an adversarial learning method for domain adaptation in the context of semantic segmentation. Considering semantic segmentations as structured outputs that contain spatial similarities between the source and target domains, we adopt adversarial learning in the output space. To further enhance the adapted model, we construct a multi-level adversarial network to effectively perform output space domain adaptation at different feature levels. Extensive experiments and ablation study are conducted under various domain adaptation settings, including synthetic-to-real and cross-city scenarios. We show that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and visual quality.
AbstractList Convolutional neural network-based approaches for semantic segmentation rely on supervision with pixel-level ground truth, but may not generalize well to unseen image domains. As the labeling process is tedious and labor intensive, developing algorithms that can adapt source ground truth labels to the target domain is of great interest. In this paper, we propose an adversarial learning method for domain adaptation in the context of semantic segmentation. Considering semantic segmentations as structured outputs that contain spatial similarities between the source and target domains, we adopt adversarial learning in the output space. To further enhance the adapted model, we construct a multi-level adversarial network to effectively perform output space domain adaptation at different feature levels. Extensive experiments and ablation study are conducted under various domain adaptation settings, including synthetic-to-real and cross-city scenarios. We show that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and visual quality.
Author Yang, Ming-Hsuan
Hung, Wei-Chih
Chandraker, Manmohan
Sohn, Kihyuk
Schulter, Samuel
Tsai, Yi-Hsuan
Author_xml – sequence: 1
  givenname: Yi-Hsuan
  surname: Tsai
  fullname: Tsai, Yi-Hsuan
– sequence: 2
  givenname: Wei-Chih
  surname: Hung
  fullname: Hung, Wei-Chih
– sequence: 3
  givenname: Samuel
  surname: Schulter
  fullname: Schulter, Samuel
– sequence: 4
  givenname: Kihyuk
  surname: Sohn
  fullname: Sohn, Kihyuk
– sequence: 5
  givenname: Ming-Hsuan
  surname: Yang
  fullname: Yang, Ming-Hsuan
– sequence: 6
  givenname: Manmohan
  surname: Chandraker
  fullname: Chandraker, Manmohan
BookMark eNotjLtOwzAUQA0CiVIyM7D4B1Ls-HXvWEW8pEhFFFgrx7GrIOJEjjPw91SC6Ryd4VyTizhGT8gtZxvOGd7Xn69vm4px2DBmgJ2RAg1wJUBrWTE8JyvOtCg1crwixTx_McYqDQKkWpG68TbFPh5pHum2s1Om-5wWl5fkO7pb8rScymSdp2FMdO8HG3PvTnIcfMw292O8IZfBfs---OeafDw-vNfPZbN7eqm3TdlXkufStmiUxABd61C0UgrRscpisB4VBmWVElZJpzFICC04g1oYITsfUBmDYk3u_r699_4wpX6w6ecAygAYEL8PXEyz
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2018.00780
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 7481
ExternalDocumentID 8578878
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-i241t-ab97549f8dbc93b4433d02a9fae959f5a553a54c69f48fb8c7963734def957793
IEDL.DBID RIE
ISICitedReferencesCount 1343
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000457843607065&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-i241t-ab97549f8dbc93b4433d02a9fae959f5a553a54c69f48fb8c7963734def957793
PageCount 10
ParticipantIDs ieee_primary_8578878
PublicationCentury 2000
PublicationDate 2018-06
PublicationDateYYYYMMDD 2018-06-01
PublicationDate_xml – month: 06
  year: 2018
  text: 2018-06
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 2.625378
Snippet Convolutional neural network-based approaches for semantic segmentation rely on supervision with pixel-level ground truth, but may not generalize well to...
SourceID ieee
SourceType Publisher
StartPage 7472
SubjectTerms Adaptation models
Image segmentation
Layout
Prediction algorithms
Semantics
Task analysis
Training
Title Learning to Adapt Structured Output Space for Semantic Segmentation
URI https://ieeexplore.ieee.org/document/8578878
WOSCitedRecordID wos000457843607065&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/eLvHCXMwlV1LTwIxEG6AePCECsZ3evDoyqPttnM0ROIJiajhRvokHHgEdv39TpcGPXjx1jZ72E4zmfnab74h5D5XVubWoCPlTmccNGQAlmXBgPG9oHPPddVsQo5GajqFcY08HGphvPcV-cw_xmH1lu_WtoxXZR0lIvdN1UldSrmv1Trcp_RzxVR6IYtzhsgmB5XUfHpd6Aw-x2-RyxXJkzLKQP5qp1JFk2Hzf_9xQto_ZXl0fAg4p6TmV2ekmfJImrx01yKDJJo6p8WaPjm9Keikkoktt_jda1lsSlxBsOwppqx04pdo3oXFwXyZSpFWbfIxfH4fvGSpWUK2wCBcZNqARKwXlDMWmOGcMdftawjag4AgtBBMC25zCFwFg0eEricZdz6AkOil56SxWq_8BaHayZ7RiE2MRXSitbaCQYjJIXAnQ_eStKJNZpu9HsYsmePq7-VrchyNvqdX3ZAG7tffkiP7VSx227vqEL8BdtKdXg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NTwIxEG0QTfSECsZve_DoKkvbbedoiAQjIhE03EjbbQkHFgK7_n7bpUEPXrx1mz3szmQy89o3bxC6TYTmiVYukJJURhQkRACaRFaBMrGViaGyHDbB-30xHsOggu62vTDGmJJ8Zu79srzLTxe68EdlD4J57pvYQbuM0la86dbanqi0EkFEuCPzz8RhmwRE0POJm_DQ_hy8ezaXp09yLwT5a6BKmU86tf99ySFq_DTm4cE25RyhismOUS1UkjjE6bqO2kE2dYrzBX5M5TLHw1Iotli5996KfFm4HQeXDXZFKx6auTPwTLvFdB6akbIG-ug8jdrdKIxLiGYuDeeRVMAd2rMiVRqIopSQtNmSYKUBBpZJxohkVCdgqbDKOckFHyc0NRYYd3F6gqrZIjOnCMuUx0o6dKK0wydSSs0IWF8eAk25bZ6hurfJZLlRxJgEc5z_vX2D9ruj196k99x_uUAH3gEbstUlqrp_N1doT3_ls_XqunToN9fHoKU
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=Learning+to+Adapt+Structured+Output+Space+for+Semantic+Segmentation&rft.au=Tsai%2C+Yi-Hsuan&rft.au=Hung%2C+Wei-Chih&rft.au=Schulter%2C+Samuel&rft.au=Sohn%2C+Kihyuk&rft.date=2018-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=7472&rft.epage=7481&rft_id=info:doi/10.1109%2FCVPR.2018.00780&rft.externalDocID=8578878