Log In Sign Up

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

by   Han Sun, et al.

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.


page 3

page 4

page 5

page 7

page 8

page 9


Progressive Multi-scale Fusion Network for RGB-D Salient Object Detection

Salient object detection(SOD) aims at locating the most significant obje...

Receptive Field Broadening and Boosting for Salient Object Detection

Salient object detection requires a comprehensive and scalable receptive...

Salient Object Detection Combining a Self-attention Module and a Feature Pyramid Network

Salient object detection has achieved great improvement by using the Ful...

Local Contrast and Global Contextual Information Make Infrared Small Object Salient Again

Infrared small object detection (ISOS) aims to segment small objects onl...

Perception-and-Regulation Network for Salient Object Detection

Effective fusion of different types of features is the key to salient ob...

Situational Perception Guided Image Matting

Most automatic matting methods try to separate the salient foreground fr...

Complementary Bi-directional Feature Compression for Indoor 360° Semantic Segmentation with Self-distillation

Recently, horizontal representation-based panoramic semantic segmentatio...