Salient Object Detection with Pyramid Attention and Salient Edges

This paper presents a new method for detecting salient objects in images using convolutional neural networks (CNNs). The proposed network, named PAGE-Net, makes two major novel contributions. The first is to devise an essential pyramid attention structure for salient object detection, which enables the network to concentrate more on salient regions while exploiting multi-scale saliency information. Such a stacked attention design offers a powerful way to efficiently enhance the representation ability of the corresponding network layer with an enlarged receptive field. The second contribution is to propose a salient edge detection module, which lies in the emphasis on the importance of salient edge information since it offers a strong cue to better segment salient objects and refine object boundaries. Such a salient edge detection module learns for precise salient boundary estimation, and thus encourages better edge-preserving salient object segmentation. Exhaustive experiments show that both of the proposed pyramid attention and salient edges are effective for salient object detection, and our PAGE-Net outperforms state-of-the-art approaches on several popular benchmarks with a fast inference speed (25FPS on a single GPU).