Back to Search
Start Over
Re-Thinking the Relations in Co-Saliency Detection.
- Source :
- IEEE Transactions on Circuits & Systems for Video Technology; Aug2022, Vol. 32 Issue 8, p5453-5466, 14p
- Publication Year :
- 2022
-
Abstract
- Co-salient object detection (CoSOD) aims to detect common salient objects sharing the same attributes in an image group. The key issue of CoSOD is how to model the inter-saliency relations within an image group. The major limitation of previous methods is that they pre-define the group-to-one relations within an image group. In this paper, we propose a new concept of structural inter-saliency relations and solve the CoSOD with deep reinforcement learning framework. Firstly, we design a semantic relation graph (SRG) to model the structural inter-saliency relations. Then the feature selecting agent (FS-agent) aims to select the informative features, which can help the SRG effectively model structural inter-saliency relations. Finally, relation updating agent (RU-agent) progressively updates the SRG to focus on the co-salient relations like human decision-making process. Extensive experiments on co-saliency datasets show that because of well modeling inter-saliency relations in image group, our proposed method achieves superior performance compared to the state-of-the-art methods. We hope that this paper can motivate future research for visual co-analysis tasks. [ABSTRACT FROM AUTHOR]
- Subjects :
- REINFORCEMENT learning
STRUCTURAL models
Subjects
Details
- Language :
- English
- ISSN :
- 10518215
- Volume :
- 32
- Issue :
- 8
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Circuits & Systems for Video Technology
- Publication Type :
- Academic Journal
- Accession number :
- 158333583
- Full Text :
- https://doi.org/10.1109/TCSVT.2022.3150923