点击次数：

论文类型：期刊论文

发表时间：2018-12-01

发表刊物：IEEE SIGNAL PROCESSING LETTERS

收录刊物：SCIE、Scopus

卷号：25

期号：12

页面范围：1800-1804

ISSN号：1070-9908

关键字：Attention; boundary information extraction; feature fusion; salient object detection

摘要：Fully convolutional networks (FCN) has significantly improved the performance of many pixel-labeling tasks, such as semantic segmentation and depth estimation. However, it still remains nontrivial to thoroughly utilize the multilevel convolutional feature maps and boundary information for salient object detection. In this letter, we propose a novel FCN framework to integrate multilevel convolutional features recurrently with the guidance of object boundary information. First, a deep convolutional network is used to extract multilevel feature maps and separately aggregate them into multiple resolutions, which can he used to generate coarse saliency maps. Meanwhile, another boundary information extraction branch is proposed to generate boundary features. Finally, an attention-based feature fusion module is designed to fuse boundary information into salient regions to achieve accurate boundary inference and semantic enhancement. The final saliency maps are the combination of the predicted boundary maps and integrated saliency maps, which are more closer to the ground truths. Experiments and analysis on four large-scale benchmarks verify that our framework achieves new state-of-the-art results.