View in EDS HTML Full Text PDF Full Text

Spatial attention-guided deformable fusion network for salient object detection.

Saved in:
Bibliographic Details
Title: Spatial attention-guided deformable fusion network for salient object detection.
Authors: Yang, Aiping1,2 (AUTHOR) yangaiping@tju.edu.cn, Liu, Yan1 (AUTHOR), Cheng, Simeng1 (AUTHOR), Cao, Jiale1 (AUTHOR), Ji, Zhong1 (AUTHOR), Pang, Yanwei1 (AUTHOR)
Source: Multimedia Systems. Oct2023, Vol. 29 Issue 5, p2563-2573. 11p.
Subjects: Struggle
Abstract: Most of salient object detection methods employ U-shape architecture as the understructure. Although promising performance has been achieved, they struggle to detect salient objects with non-rigid shapes and arbitrary sizes. Besides, the features are transmitted to the decoder directly without any discrimination and active selection, resulting in prominent features underutilized. To address the above issues, we propose a spatial-attention-guided deformable fusion network for salient object detection, which consists of a contour enhancement module (CEM), a spatial-attention-guided deformable fusion module (SADFM) and a gate module (GM). Specifically, the CEM is designed to obtain global features, aiming to reduce the loss of high-level features in the transfer process. The SADFM develops the spatial attention to guide the deformable convolution to aggregate global features, high-level and low-level features adaptively. Furthermore, the GM is employed to refine the initial fusion features and predict the salient regions accurately. Experiments on five public datasets verify the effectiveness of our method. [ABSTRACT FROM AUTHOR]
Copyright of Multimedia Systems is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 171993664
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Spatial attention-guided deformable fusion network for salient object detection.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Yang%2C+Aiping%22">Yang, Aiping</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> yangaiping@tju.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Liu%2C+Yan%22">Liu, Yan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Cheng%2C+Simeng%22">Cheng, Simeng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Cao%2C+Jiale%22">Cao, Jiale</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ji%2C+Zhong%22">Ji, Zhong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Pang%2C+Yanwei%22">Pang, Yanwei</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Multimedia+Systems%22">Multimedia Systems</searchLink>. Oct2023, Vol. 29 Issue 5, p2563-2573. 11p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Struggle%22">Struggle</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Most of salient object detection methods employ U-shape architecture as the understructure. Although promising performance has been achieved, they struggle to detect salient objects with non-rigid shapes and arbitrary sizes. Besides, the features are transmitted to the decoder directly without any discrimination and active selection, resulting in prominent features underutilized. To address the above issues, we propose a spatial-attention-guided deformable fusion network for salient object detection, which consists of a contour enhancement module (CEM), a spatial-attention-guided deformable fusion module (SADFM) and a gate module (GM). Specifically, the CEM is designed to obtain global features, aiming to reduce the loss of high-level features in the transfer process. The SADFM develops the spatial attention to guide the deformable convolution to aggregate global features, high-level and low-level features adaptively. Furthermore, the GM is employed to refine the initial fusion features and predict the salient regions accurately. Experiments on five public datasets verify the effectiveness of our method. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Multimedia Systems is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=171993664
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00530-023-01152-4
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 2563
    Subjects:
      – SubjectFull: Struggle
        Type: general
    Titles:
      – TitleFull: Spatial attention-guided deformable fusion network for salient object detection.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Yang, Aiping
      – PersonEntity:
          Name:
            NameFull: Liu, Yan
      – PersonEntity:
          Name:
            NameFull: Cheng, Simeng
      – PersonEntity:
          Name:
            NameFull: Cao, Jiale
      – PersonEntity:
          Name:
            NameFull: Ji, Zhong
      – PersonEntity:
          Name:
            NameFull: Pang, Yanwei
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: Oct2023
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-print
              Value: 09424962
          Numbering:
            – Type: volume
              Value: 29
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: Multimedia Systems
              Type: main
ResultId 1