Cascaded Interaction with Eroded Deep Supervision for Salient Object Detection

TL;DR

This paper introduces a novel cascaded interaction network with global-local aligned attention and a deep supervision strategy based on edge erosion, significantly improving salient object detection by mitigating information distortion caused by interpolation.

Contribution

It proposes a new network architecture with GAA guidance and edge erosion-based deep supervision to address interpolation issues in salient object detection.

Findings

Outperforms existing methods on five datasets

Reduces information distortion from interpolation

Enhances feature and label guidance effectiveness

Abstract

Deep convolutional neural networks have been widely applied in salient object detection and have achieved remarkable results in this field. However, existing models suffer from information distortion caused by interpolation during up-sampling and down-sampling. In response to this drawback, this article starts from two directions in the network: feature and label. On the one hand, a novel cascaded interaction network with a guidance module named global-local aligned attention (GAA) is designed to reduce the negative impact of interpolation on the feature side. On the other hand, a deep supervision strategy based on edge erosion is proposed to reduce the negative guidance of label interpolation on lateral output. Extensive experiments on five popular datasets demonstrate the superiority of our method.