Multistep feature aggregation framework for salient object detection

TL;DR

This paper introduces a multistep feature aggregation framework for salient object detection that enhances multi-level feature fusion, leading to more accurate saliency maps and state-of-the-art performance on benchmark datasets.

Contribution

The proposed MSFA framework with three modules improves feature fusion in salient object detection, addressing limitations of previous one-way methods.

Findings

Achieves state-of-the-art results on six benchmark datasets.

Improves accuracy of saliency maps compared to previous methods.

Demonstrates effective multi-level feature integration.

Abstract

Recent works on salient object detection have made use of multi-scale features in a way such that high-level features and low-level features can collaborate in locating salient objects. Many of the previous methods have achieved great performance in salient object detection. By merging the high-level and low-level features, a large number of feature information can be extracted. Generally, they are doing these in a one-way framework, and interweaving the variable features all the way to the final feature output. Which may cause some blurring or inaccurate localization of saliency maps. To overcome these difficulties, we introduce a multistep feature aggregation (MSFA) framework for salient object detection, which is composed of three modules, including the Diverse Reception (DR) module, multiscale interaction (MSI) module and Feature Enhancement (FE) module to accomplish better multi-level feature fusion. Experimental results on six benchmark datasets demonstrate that MSFA achieves state-of-the-art performance.