中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Hierarchical Feature Fusion Network for Salient Object Detection

文献类型:期刊论文

作者Li, Xuelong3; Song, Dawei1,2; Dong, Yongsheng3
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2020
卷号29页码:9165-9175
关键词Feature extraction Semantics Image edge detection Object detection Fuses Visualization Image color analysis Salient object detection hierarchical feature fusion edge information-guided one-to-one hierarchical supervision strategy
ISSN号1057-7149;1941-0042
DOI10.1109/TIP.2020.3023774
产权排序2
英文摘要

Convolutional Neural Network (CNN) has shown their advantages in salient object detection. CNN can generate great saliency maps because it can obtain high-level semantic information. And the semantic information is usually achieved by stacking multiple convolutional layers and pooling layers. However, multiple pooling operations will reduce the size of the feature map and easily blur the boundary of the salient object. Therefore, such operations are not beneficial to generate great saliency results. To alleviate this issue, we propose a novel edge information-guided hierarchical feature fusion network (HFFNet). Our network fuses features hierarchically and retains accurate semantic information and clear edge information effectively. Specifically, we extract image features from different levels of VGG. Then, we fuse the features hierarchically to generate high-level semantic information and low-level edge information. In order to retain better information at different levels, we adopt a one-to-one hierarchical supervision strategy to supervise the generation of low-level information and high-level information respectively. Finally, we use low-level edge information to guide the saliency map generation, and the edge guidance fusion is able to identify saliency regions effectively. The proposed HFFNet has been extensively evaluated on five traditional benchmark datasets. The experimental results demonstrate that the proposed model is fairly effective in salient object detection compared with 10 state-of-the-art models under different evaluation indicators, and it is superior to most of the comparison models.

语种英语
WOS记录号WOS:000574739100003
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://ir.opt.ac.cn/handle/181661/93728]  
专题西安光学精密机械研究所_光学影像学习与分析中心
通讯作者Dong, Yongsheng
作者单位1.Univ Chinese Acad Sci, Sch Optoelect, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Shaanxi Key Lab Ocean Opt, Xian 710119, Peoples R China
3.Northwestern Polytech Univ, Ctr OPT IMagery Anal & Learning OPTIMAL, Xian 710072, Peoples R China
推荐引用方式
GB/T 7714
Li, Xuelong,Song, Dawei,Dong, Yongsheng. Hierarchical Feature Fusion Network for Salient Object Detection[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:9165-9175.
APA Li, Xuelong,Song, Dawei,&Dong, Yongsheng.(2020).Hierarchical Feature Fusion Network for Salient Object Detection.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,9165-9175.
MLA Li, Xuelong,et al."Hierarchical Feature Fusion Network for Salient Object Detection".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):9165-9175.

入库方式: OAI收割

来源:西安光学精密机械研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。