Cascaded Interaction with Eroded Deep Supervision for Salient Object Detection
This work addresses a specific technical issue in computer vision for salient object detection, representing an incremental improvement.
The paper tackled the problem of information distortion from interpolation in salient object detection by proposing a cascaded interaction network with global-local aligned attention and an eroded deep supervision strategy, achieving superior results on five datasets.
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.