Salient object detection by aggregating contextual information

Yan Liu, Yunzhou Zhang, Shichang Liu, Sonya Coleman, Zhenyu Wang, Feng Qiu

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

Salient object detection is a fundamental computer vision task. Deep learning techniques have been successfully applied for salient object detection, however, the saliency maps still suffer from incomplete predictions owing to the difficulty and complexity of objects. We propose a novel convolutional neural network based on aggregating contextual information that can improve the accuracy of salient object detection. In order to obtain high-level global information for fine-level feature maps, we add a pyramid pooling module to the proposed network. Moreover, building a guiding module that consists of four context-information feature modules, the algorithm can gain more effective information and enrich the details of saliency maps. Extensive experiments conducted using six benchmark datasets demonstrate that the proposed method outperforms existing state-of-the-art algorithms.

Original languageEnglish
Pages (from-to)190-199
Number of pages10
JournalPattern Recognition Letters
Volume153
Early online date21 Dec 2021
DOIs
Publication statusPublished (in print/issue) - 31 Jan 2022

Bibliographical note

Funding Information:
This work was supported by Major Science and technology innovation engineering projects of Shandong Province (2019JZZY010128), National Natural Science Foundation of China (Nos. 61973066 , 61471110, 61906176 ), Fundation of Key Laboratory of Aerospace System Simulation(61420020301), Fundamental Research Funds for the Central Universities ( N182608004 ) and the Distinguished Creative Talent Program of Liaoning Colleges and Universities (LR2019027 ).

Publisher Copyright:
© 2021 Elsevier B.V.

Keywords

  • Aggregating contextual information
  • Convolutional neural network
  • Salient object detection

Fingerprint

Dive into the research topics of 'Salient object detection by aggregating contextual information'. Together they form a unique fingerprint.

Cite this