Addressing Multiple Salient Object Detection via Dual-Space Long-Range Dependencies
This addresses the challenge of multiple salient object detection for computer vision applications, representing an incremental advance with a novel method for a known bottleneck.
The paper tackles the problem of detecting multiple salient objects in complex scenes by proposing a network that captures long-range dependencies in spatial and channel spaces, achieving state-of-the-art results on five datasets and further improvements on a new curated multi-object dataset.
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 avaliable at: https://github.com/EricDengbowen/DSLRDNet.