Cross refinement network with edge detection for salient object detection

Abstract

Salient object detection aims to identify the most attractive objects from images. However, their boundaries are typically of poor quality when predicted using available methods. One or multiple objects may also be left undetected if the image contains multiple objects. To solve these problems, this article proposes the novel cross refinement network, which consists of a Res2Net‐based backbone network; a fusion network equipped with four convolutional block attention modules and four edge‐salient cross units; and a detection network with an edge enhancement unit and a residual refinement network (RNN). For RNN training, the rough salient maps generated using the DUTS‐TR dataset are treated as a special training dataset. Compared to existing methods, the proposed network can effectively detect all objects as well as improve the boundaries of the detected objects by performing experiments on five benchmark datasets. Based on the experimental results, the proposed network outperforms existing methods both objectively and subjectively.