Addressing multiple salient object detection via dual-space long-range dependencies

Deng, Bowen; French, Andrew P.; Pound, Michael P.

Abstract

Salient object detection plays an important role in many downstream tasks. However, complex real-world scenes with varying scales and numbers of salient objects still pose a challenge. In this paper, we directly address the problem of detecting multiple salient objects across complex scenes. We propose a network architecture incorporating non-local feature information in both the spatial and channel spaces, capturing the long-range dependencies between separate objects. Traditional bottom-up and non-local features are combined with edge features within a feature fusion gate that progressively refines the salient object prediction in the decoder. We show that our approach accurately locates multiple salient regions even in complex scenarios. To demonstrate the efficacy of our approach to the multiple salient objects problem, we curate a new dataset containing only multiple salient objects. Our experiments demonstrate the proposed method presents state-of-the-art results on five widely used datasets without any pre-processing and post-processing. We obtain a further performance improvement against competing techniques on our multi-objects dataset. The dataset and source code are available at: https://github.com/EricDengbowen/DSLRDNet

Citation

Deng, B., French, A. P., & Pound, M. P. (2023). Addressing multiple salient object detection via dual-space long-range dependencies. Computer Vision and Image Understanding, 235, Article 103776. https://doi.org/10.1016/j.cviu.2023.103776

• Journal Article Type: Article
• Acceptance Date: Jul 4, 2023
• Online Publication Date: Jul 8, 2023
• Publication Date: 2023-10
• Deposit Date: Jul 12, 2023
• Publicly Available Date: Jul 13, 2023
• Journal: Computer Vision and Image Understanding
• Print ISSN: 1077-3142
• Electronic ISSN: 1090-235X
• Publisher: Elsevier BV
• Peer Reviewed: Peer Reviewed
• Volume: 235
• Article Number: 103776
• DOI: https://doi.org/10.1016/j.cviu.2023.103776
• Keywords: Salient object detection; Attention; Dual-space long-range dependencies; Non-local neural networks
• Public URL: https://nottingham-repository.worktribe.com/output/22996727
• Publisher URL: https://www.sciencedirect.com/science/article/pii/S107731422300156X