Addressing Multiple Salient Object Detection via Dual-Space Long-Range Dependencies

TL;DR

This paper introduces a novel neural network architecture that effectively detects multiple salient objects in complex scenes by capturing long-range dependencies in both spatial and channel dimensions, achieving state-of-the-art results.

Contribution

The paper proposes a dual-space long-range dependency network with a feature fusion gate, and introduces a new dataset for multiple salient object detection, advancing the accuracy in complex scenarios.

Findings

Achieves state-of-the-art performance on five datasets.

Effectively locates multiple salient objects in complex scenes.

Demonstrates improved results on a newly curated multi-object dataset.

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 avaliable at: https://github.com/EricDengbowen/DSLRDNet.