A novel graph structure for salient object detection based on divergence background and compact foreground

TL;DR

This paper introduces a new graph-based model for salient object detection that leverages divergence background and compact foreground cues, using a virtual node and an Extended Manifold Ranking algorithm to improve detection accuracy.

Contribution

The paper presents a novel graph structure with a virtual node and an EMR algorithm, enhancing the distinction between object boundaries and regions for better saliency detection.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Achieves significant improvements in detection accuracy

Demonstrates robustness across various evaluation metrics

Abstract

In this paper, we propose an efficient and discriminative model for salient object detection. Our method is carried out in a stepwise mechanism based on both divergence background and compact foreground cues. In order to effectively enhance the distinction between nodes along object boundaries and the similarity among object regions, a graph is constructed by introducing the concept of virtual node. To remove incorrect outputs, a scheme for selecting background seeds and a method for generating compactness foreground regions are introduced, respectively. Different from prior methods, we calculate the saliency value of each node based on the relationship between the corresponding node and the virtual node. In order to achieve significant performance improvement consistently, we propose an Extended Manifold Ranking (EMR) algorithm, which subtly combines suppressed / active nodes and mid-level information. Extensive experimental results demonstrate that the proposed algorithm performs favorably against the state-of-art saliency detection methods in terms of different evaluation metrics on several benchmark datasets.