Perception-and-Regulation Network for Salient Object Detection

TL;DR

This paper introduces a novel feature fusion network for salient object detection that employs a perception-regulation attention mechanism and an imitation eye observation module to improve global perception and adaptively fuse features.

Contribution

It proposes the perception-and-regulation (PR) block and IEO module, which explicitly model feature interdependencies and mimic human vision for enhanced saliency detection.

Findings

Outperforms 22 state-of-the-art methods on SOD datasets.

Effectively models feature relationships with the PR block.

Enhances global perception with the IEO module.

Abstract

Effective fusion of different types of features is the key to salient object detection. The majority of existing network structure design is based on the subjective experience of scholars and the process of feature fusion does not consider the relationship between the fused features and highest-level features. In this paper, we focus on the feature relationship and propose a novel global attention unit, which we term the "perception- and-regulation" (PR) block, that adaptively regulates the feature fusion process by explicitly modeling interdependencies between features. The perception part uses the structure of fully-connected layers in classification networks to learn the size and shape of objects. The regulation part selectively strengthens and weakens the features to be fused. An imitating eye observation module (IEO) is further employed for improving the global perception ability of the network. The imitation of foveal vision and peripheral vision enables IEO to scrutinize highly detailed objects and to organize the broad spatial scene to better segment objects. Sufficient experiments conducted on SOD datasets demonstrate that the proposed method performs favorably against 22 state-of-the-art methods.