Focal Boundary Guided Salient Object Detection

doi:10.1109/TIP.2019.2891055

	Focal Boundary Guided Salient Object Detection
	Wang, Yupei1,2 ; Zhao, Xin1,2 ; Hu, Xuecai 3,4; Li, Yin 5,6; Huang, Kaiqi2,7,8
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2019-06-01
卷号	28 期号:6 页码:2813-2824
关键词	Visual saliency detection salient object segmentation boundary detection deep learning
ISSN号	1057-7149
DOI	10.1109/TIP.2019.2891055
通讯作者	Huang, Kaiqi(kqhuang@nlpr.ia.ac.cn)
英文摘要	The performance of salient object segmentation has been significantly advanced by using the deep convolutional networks. However, these networks often produce blob-like saliency maps without accurate object boundaries. This is caused by the limited spatial resolution of their feature maps after multiple pooling operations and might hinder downstream applications that require precise object shapes. To address this issue, we propose a novel deep model-Focal Boundary Guided (Focal-BG) network. Our model is designed to jointly learn to segment salient object masks and detect salient object boundaries. Our key idea is that additional knowledge about object boundaries can help to precisely identify the shape of the object. Moreover, our model incorporates a refinement pathway to refine the mask prediction and makes use of the focal lass to facilitate the learning of the hard boundary pixels. To evaluate our model, we conduct extensive experiments. Our Focal-BG network consistently outperforms the state-of-the-art methods on five major benchmarks. We provide a detailed analysis of these results and demonstrate that our joint modeling of salient object boundary and mask helps to better capture the shape details, especially in the vicinity of object boundaries.
资助项目	National Key Research and Development Program of China[2016YFB1001005] ; National Natural Science Foundation of China[61673375] ; National Natural Science Foundation of China[61602485] ; National Natural Science Foundation of China[61721004] ; Chinese Academy of Science[QYZDB-SSW-JSC006] ; Chinese Academy of Science[173211KYSB20160008]
WOS关键词	MODEL
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000462386000014
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Chinese Academy of Science
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/23350]
专题	中国科学院自动化研究所自动化研究所_智能感知与计算研究中心
通讯作者	Huang, Kaiqi
作者单位	1.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Syst & Engn, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230026, Anhui, Peoples R China 5.Univ Wisconsin, Dept Biostat & Med Informat, Madison, WI 53706 USA 6.Univ Wisconsin, Dept Comp Sci, 1210 W Dayton St, Madison, WI 53706 USA 7.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Syst & Engn, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 8.CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 20031, Peoples R China
推荐引用方式 GB/T 7714	Wang, Yupei,Zhao, Xin,Hu, Xuecai,et al. Focal Boundary Guided Salient Object Detection[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2019,28(6):2813-2824.
APA	Wang, Yupei,Zhao, Xin,Hu, Xuecai,Li, Yin,&Huang, Kaiqi.(2019).Focal Boundary Guided Salient Object Detection.IEEE TRANSACTIONS ON IMAGE PROCESSING,28(6),2813-2824.
MLA	Wang, Yupei,et al."Focal Boundary Guided Salient Object Detection".IEEE TRANSACTIONS ON IMAGE PROCESSING 28.6(2019):2813-2824.