MPI: Multi-receptive and Parallel Integration for Salient Object Detection

TL;DR

This paper introduces MPI, a novel salient object detection method that enhances feature representation through multi-receptive modules and improves feature fusion with a parallel strategy, leading to superior performance.

Contribution

The paper proposes a multi-receptive enhancement module and a parallel fusion strategy to improve semantic feature representation and interaction in salient object detection.

Findings

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

Enhances semantic representation with multi-receptive modules

Improves feature interaction through parallel fusion strategy

Abstract

The semantic representation of deep features is essential for image context understanding, and effective fusion of features with different semantic representations can significantly improve the model's performance on salient object detection. In this paper, a novel method called MPI is proposed for salient object detection. Firstly, a multi-receptive enhancement module (MRE) is designed to effectively expand the receptive fields of features from different layers and generate features with different receptive fields. MRE can enhance the semantic representation and improve the model's perception of the image context, which enables the model to locate the salient object accurately. Secondly, in order to reduce the reuse of redundant information in the complex top-down fusion method and weaken the differences between semantic features, a relatively simple but effective parallel fusion strategy (PFS) is proposed. It allows multi-scale features to better interact with each other, thus improving the overall performance of the model. Experimental results on multiple datasets demonstrate that the proposed method outperforms state-of-the-art methods under different evaluation metrics.