ERBANet: Enhancing region and boundary awareness for salient object detection

Abstract

Existing methods based on convolutional neural networks (CNNs) have progressed significantly in the salient object detection task. However, in some cases, the accurate detection of intact objects and maintenance of their original detailed structures, such as boundaries, was not possible. In this paper, we propose an Enhancing Region and Boundary Awareness Network (ERBANet), equipped with attentional feature enhancement (AFE) modules to improve the detection performance. The AFE modules act on high-level and low-level features to generate corresponding attentional features. High-level attentional features are used to highlight entire salient objects, while low-level attentional features help retain their boundaries. The proposed ERBANet aims to effectively aggregate high-level and low-level attentional features, fully utilizing their respective advantages. Furthermore, we propose a novel boundary maintenance loss (BML) for learning to preserve the original boundaries of salient objects. Meanwhile, dice loss is combined for learning to enhance the integrity of salient regions. The experimental results on five benchmark datasets demonstrate that our proposed method outperforms recent state-of-the-art methods and achieves better performance.