OPT OpenIR  > 海洋光学技术研究室
Hierarchical Edge Refinement Network for Saliency Detection
Song, Dawei1,2; Dong, Yongsheng3,4; Li, Xuelong3,4
作者部门海洋光学技术研究室
2021
发表期刊IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN1057-7149;1941-0042
卷号30页码:7567-7577
产权排序1
摘要

At present, most saliency detection methods are based on fully convolutional neural networks (FCNs). However, FCNs usually blur the edges of salient objects. Due to that, the multiple convolution and pooling operations of the FCNs will limit the spatial resolution of the feature maps. To alleviate this issue and obtain accurate edges, we propose a hierarchical edge refinement network (HERNet) for accurate saliency detection. In detail, the HERNet is mainly composed of a saliency prediction network and an edge preserving network. Firstly, the saliency prediction network is used to roughly detect the regions of salient objects and is based on a modified U-Net structure. Then, the edge preserving network is used to accurately detect the edges of salient objects, and this network is mainly composed of the atrous spatial pyramid pooling (ASPP) module. Different from the previous indiscriminate supervision strategy, we adopt a new one-to-one hierarchical supervision strategy to supervise the different outputs of the entire network. Experimental results on five traditional benchmark datasets demonstrate that the proposed HERNet performs well when compared with the state-of-the-art methods.

关键词Image edge detection Feature extraction Saliency detection Data mining Convolution Semantics Visualization Saliency detection edge preserving network atrous spatial pyramid pooling module one-to-one hierarchical supervision strategy
DOI10.1109/TIP.2021.3106798
收录类别SCI ; EI
语种英语
WOS记录号WOS:000693758500004
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
EI入藏号20213710897470
引用统计
被引频次:8[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.opt.ac.cn/handle/181661/95068
专题海洋光学技术研究室
通讯作者Li, Xuelong
作者单位1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Shaanxi Key Lab Ocean Opt, Xian 710119, Peoples R China
2.Univ Chinese Acad Sci, Sch Optoelect, Beijing 100049, Peoples R China
3.Northwestern Polytech Univ, Sch Artificial Intelligence Opt & Elect iOPEN, Xian 710072, Peoples R China
4.Northwestern Polytech Univ, Minist Ind & Informat Technol, Key Lab Intelligent Interact & Applicat, Xian 710072, Peoples R China
推荐引用方式
GB/T 7714
Song, Dawei,Dong, Yongsheng,Li, Xuelong. Hierarchical Edge Refinement Network for Saliency Detection[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2021,30:7567-7577.
APA Song, Dawei,Dong, Yongsheng,&Li, Xuelong.(2021).Hierarchical Edge Refinement Network for Saliency Detection.IEEE TRANSACTIONS ON IMAGE PROCESSING,30,7567-7577.
MLA Song, Dawei,et al."Hierarchical Edge Refinement Network for Saliency Detection".IEEE TRANSACTIONS ON IMAGE PROCESSING 30(2021):7567-7577.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Hierarchical Edge Re(3064KB)期刊论文出版稿开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Song, Dawei]的文章
[Dong, Yongsheng]的文章
[Li, Xuelong]的文章
百度学术
百度学术中相似的文章
[Song, Dawei]的文章
[Dong, Yongsheng]的文章
[Li, Xuelong]的文章
必应学术
必应学术中相似的文章
[Song, Dawei]的文章
[Dong, Yongsheng]的文章
[Li, Xuelong]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Hierarchical Edge Refinement Network for Saliency Detection.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。