文献类型：期刊文献

英文题名：Residual attentive feature learning network for salient object detection

作者：Zhang, Qing[1];Shi, Yanjiao[1];Zhang, Xueqin[2];Zhang, Liqian[1]

机构：[1]Shanghai Inst Technol, Sch Comp Sci & Informat Engn, Shanghai 201418, Peoples R China;[2]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China

年份：2022

卷号：501

起止页码：741

外文期刊名：NEUROCOMPUTING

收录：;EI(收录号：20222712318774);WOS:【SCI-EXPANDED(收录号:WOS:000829601500007)】；

基金：Acknowledgment This work is supported by National Science Foundation of Shanghai under Grant Nos.19ZR1455300, 21ZR1462600 and 19ZR1455200, and National Natural Science Foundation of China under Grant No.61806126.

语种：英文

外文关键词：Salient object detection; Saliency detection; Attention; Residual learning; Multi -level feature integration

摘要：Salient object detection is one of the basic challenging problems in the area of computer vision. Traditional saliency models usually utilize handcrafted features and various prior cues to locate and segment salient objects from complicated surroundings. Recently, with the development of convolutional neural networks (CNNs), most of existing approaches explore the combination of multi-level feature maps for improving detection performance. However, how to learn powerful feature is still a challenge, and the multi-level and multi-scale feature maps are usually aggregated without distinction. In this paper, we propose a novel salient object detection approach named residual attentive feature learning (RAFL) to uniformly highlight salient objects and effectively suppress background noises. In our proposed RAFL, a global perception (GP) module is designed to obtain rich global features of input image. A pyramid feature extraction (PFE) module is utilized to capture the rich context of side-output information. Moreover, an attentive feature selection (AFS) module is applied to refine these side-output features and generate attentive features, so as to find out the important feature channels having high responses to the salient objects. Finally, a residual feature learning (RFL) module is proposed to make the shallow layers generate more accurate saliency maps with the help of the deep layers which contain more global semantic information. Experimental results show that our proposed approach performs favorably against 18 state-of-the-art representative methods on five benchmark datasets.(c) 2022 Elsevier B.V. All rights reserved.