Stacked Cross Refinement Network for Edge-Aware Salient Object Detection

Salient object detection is a fundamental computer vision task. The majority of existing algorithms focus on aggregating multi-level features of pre-trained convolutional neural networks. Moreover, some researchers attempt to utilize edge information for auxiliary training. However, existing edge-aw...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings / IEEE International Conference on Computer Vision s. 7263 - 7272
Hlavní autori: Wu, Zhe, Su, Li, Huang, Qingming
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.10.2019
Predmet:
ISSN:2380-7504
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Salient object detection is a fundamental computer vision task. The majority of existing algorithms focus on aggregating multi-level features of pre-trained convolutional neural networks. Moreover, some researchers attempt to utilize edge information for auxiliary training. However, existing edge-aware models design unidirectional frameworks which only use edge features to improve the segmentation features. Motivated by the logical interrelations between binary segmentation and edge maps, we propose a novel Stacked Cross Refinement Network (SCRN) for salient object detection in this paper. Our framework aims to simultaneously refine multi-level features of salient object detection and edge detection by stacking Cross Refinement Unit (CRU). According to the logical interrelations, the CRU designs two direction-specific integration operations, and bidirectionally passes messages between the two tasks. Incorporating the refined edge-preserving features with the typical U-Net, our model detects salient objects accurately. Extensive experiments conducted on six benchmark datasets demonstrate that our method outperforms existing state-of-the-art algorithms in both accuracy and efficiency. Besides, the attribute-based performance on the SOC dataset show that the proposed model ranks first in the majority of challenging scenes. Code can be found at https://github.com/wuzhe71/SCAN.
AbstractList Salient object detection is a fundamental computer vision task. The majority of existing algorithms focus on aggregating multi-level features of pre-trained convolutional neural networks. Moreover, some researchers attempt to utilize edge information for auxiliary training. However, existing edge-aware models design unidirectional frameworks which only use edge features to improve the segmentation features. Motivated by the logical interrelations between binary segmentation and edge maps, we propose a novel Stacked Cross Refinement Network (SCRN) for salient object detection in this paper. Our framework aims to simultaneously refine multi-level features of salient object detection and edge detection by stacking Cross Refinement Unit (CRU). According to the logical interrelations, the CRU designs two direction-specific integration operations, and bidirectionally passes messages between the two tasks. Incorporating the refined edge-preserving features with the typical U-Net, our model detects salient objects accurately. Extensive experiments conducted on six benchmark datasets demonstrate that our method outperforms existing state-of-the-art algorithms in both accuracy and efficiency. Besides, the attribute-based performance on the SOC dataset show that the proposed model ranks first in the majority of challenging scenes. Code can be found at https://github.com/wuzhe71/SCAN.
Author Wu, Zhe
Su, Li
Huang, Qingming
Author_xml – sequence: 1
  givenname: Zhe
  surname: Wu
  fullname: Wu, Zhe
  organization: University of Chinese Academy of Sciences
– sequence: 2
  givenname: Li
  surname: Su
  fullname: Su, Li
  organization: University of Chinese Academy of Sciences
– sequence: 3
  givenname: Qingming
  surname: Huang
  fullname: Huang, Qingming
  organization: University of Chinese Academy of Sciences
BookMark eNotkM1KAzEYRaMo2NauXbjJC0z9kkz-lmWstlAsWHVbMpkvkv7MSCZQfHtHdHUWFw6XMyZXbdciIXcMZoyBfVhV1ceMA7MzAC3UBZlabZjmhpUGhLkkIy4MFFpCeUPGfb8HEJYbNSLLbXb-gA2tUtf39BVDbPGEbaYvmM9dOtDQJbpoPrGYn11CunXH-Dtv6j36TB8xD4hde0uugzv2OP3nhLw_Ld6qZbHePK-q-bqIXNlcMKWk97qpG9SBC0AbmAsaApOCc1VbFMbL2pZeoQOEMNyXVqLlQUkpajEh93_eiIi7rxRPLn3vLAwZZCl-AL9uTTw
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICCV.2019.00736
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 9781728148038
1728148030
EISSN 2380-7504
EndPage 7272
ExternalDocumentID 9010954
Genre orig-research
GroupedDBID 29O
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IPLJI
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i269t-1665cc7dbde7f230e9f1af70f153226b9e38c5b94c6ea0e0f038595e92f6553b3
IEDL.DBID RIE
ISICitedReferencesCount 400
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000548549202037&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 02:38:46 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i269t-1665cc7dbde7f230e9f1af70f153226b9e38c5b94c6ea0e0f038595e92f6553b3
PageCount 10
ParticipantIDs ieee_primary_9010954
PublicationCentury 2000
PublicationDate 2019-10-01
PublicationDateYYYYMMDD 2019-10-01
PublicationDate_xml – month: 10
  year: 2019
  text: 2019-10-01
  day: 01
PublicationDecade 2010
PublicationTitle Proceedings / IEEE International Conference on Computer Vision
PublicationTitleAbbrev ICCV
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0039286
Score 2.6000228
Snippet Salient object detection is a fundamental computer vision task. The majority of existing algorithms focus on aggregating multi-level features of pre-trained...
SourceID ieee
SourceType Publisher
StartPage 7263
SubjectTerms Computational modeling
Feature extraction
Image edge detection
Image segmentation
Object detection
Silicon
Task analysis
Title Stacked Cross Refinement Network for Edge-Aware Salient Object Detection
URI https://ieeexplore.ieee.org/document/9010954
WOSCitedRecordID wos000548549202037&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/eLvHCXMwlV1LTwMhEJ60jQdPVVvjOxw8urb7AJajWdvUxNTGV3prFhhML61pt_r3ZXbX6sGLNwIEwhCYD_jmA-AyV0kuJaoAjcUgsVoHCq3zQC4OY82TyOhSZ_ZejsfpdKomDbjaxsIgYkk-w2tKlm_5dmk2dFXWIyqB4kkTmlKKKlbre9f1bj4VtXSPr9S7y7JXIm6RGqUk_eVff6eUrmPY_l-ne9D9icFjk6132YcGLg6gXYNGVi_JdQdGHi76lWhZRv6OPaLzuJGaZOOK4c08LGUD-4bBzWe-QvbkkTcVP2i6gmG3WJRsrEUXXoaD52wU1N8jBPNIqCIIheDGSKstSudPEqhcmDvZd34T86BKK4xTw7VKjMC8j31Hj4CKo4qc4DzW8SG0FssFHgEjk-Vh6ocakQBgoh2PpFBpYoXKPUg4hg4ZZvZeKWDMapuc_J19Crtk-YrydgatYrXBc9gxH8V8vboop-0LlWiZBQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LTgMhFCW1muiqamt8y8KlY-fBY1ia0aaNdWy0mu6aAS6mm6lpp_r7wsxYXbhxR4BAuATuAc49IHSZCZJxDsIDpcEjWkpPgDYWyEVBJCkJlSx1Zoc8TePJRIwa6GodCwMAJfkMrl2yfMvXc7VyV2VdRyUQlGygTUpI6FfRWt_7rnX0MavFe2y17iBJXh11y-lRcqfA_Ov3lNJ59Fr_63YXdX6i8PBo7V_2UAPyfdSqYSOuF-WyjfoWMNq1qHHiPB5-AmORo2sSpxXHG1tgiu_0G3g3n9kC8LPF3q74UbpLGHwLRcnHyjvopXc3Tvpe_UGCNwuZKLyAMaoU11IDN_YsAcIEmeG-sduYhVVSQBQrKgVRDDIffOOeAQUFERpGaSSjA9TM5zkcIuxMlgWxHWroJACJNDTkTMREM5FZmHCE2s4w0_dKA2Na2-T47-wLtN0fPwynw0F6f4J23CxUBLhT1CwWKzhDW-qjmC0X5-UUfgG9XZxM
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=Proceedings+%2F+IEEE+International+Conference+on+Computer+Vision&rft.atitle=Stacked+Cross+Refinement+Network+for+Edge-Aware+Salient+Object+Detection&rft.au=Wu%2C+Zhe&rft.au=Su%2C+Li&rft.au=Huang%2C+Qingming&rft.date=2019-10-01&rft.pub=IEEE&rft.eissn=2380-7504&rft.spage=7263&rft.epage=7272&rft_id=info:doi/10.1109%2FICCV.2019.00736&rft.externalDocID=9010954