Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis

doi:10.1109/TPAMI.2016.2522415

	Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis
	Liu, Risheng 1; Zhong, Guangyu 2; Cao, Junjie 2; Lin, Zhouchen 3,4; Shan, Shiguang 5; Luo, Zhongxuan 1
	2016-12-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	38 期号:12 页码:2457-2471
摘要	Partial differential equations (PDEs) have been used to formulate image processing for several decades. Generally, a PDE system consists of two components: the governing equation and the boundary condition. In most previous work, both of them are generally designed by people using mathematical skills. However, in real world visual analysis tasks, such predefined and fixed-form PDEs may not be able to describe the complex structure of the visual data. More importantly, it is hard to incorporate the labeling information and the discriminative distribution priors into these PDEs. To address above issues, we propose a new PDE framework, named learning to diffuse (LTD), to adaptively design the governing equation and the boundary condition of a diffusion PDE system for various vision tasks on different types of visual data. To our best knowledge, the problems considered in this paper (i.e., saliency detection and object tracking) have never been addressed by PDE models before. Experimental results on various challenging benchmark databases show the superiority of LTD against existing state-of-the-art methods for all the tested visual analysis tasks.
关键词	Visual diffusion PDE governed combinatorial optimization submodularity saliency detection object tracking
DOI	10.1109/TPAMI.2016.2522415
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China (NSFC)[61300086] ; National Natural Science Foundation of China (NSFC)[61432003] ; Fundamental Research Funds for the Central Universities[DUT15QY15] ; Hong Kong Scholar Program[XJ2015008] ; China Scholarship Council ; NSFC[61363048] ; NSFC[61272341] ; NSFC[61231002] ; NSFC[61222211] ; National Basic Research Program of China (973 Program)[2015CB352502] ; Microsoft Research Asia Collaborative Research Program
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000387984700009
出版者	IEEE COMPUTER SOC
引用统计	被引频次：33[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/7895
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Risheng
作者单位	1.Dalian Univ Technol, Sch Software Technol, Key Lab Ubiquitous Network & Serv Software Liaoni, Dalian, Peoples R China 2.Dalian Univ Technol, Sch Math Sci, Dalian, Peoples R China 3.Peking Univ, Sch Elect Engn & Comp Sci, Key Lab Machine Percept MOE, Beijing, Peoples R China 4.Shanghai Jiao Tong Univ, Cooperat Medianet Innovat Ctr, Shanghai, Peoples R China 5.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Liu, Risheng,Zhong, Guangyu,Cao, Junjie,et al. Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2016,38(12):2457-2471.
APA	Liu, Risheng,Zhong, Guangyu,Cao, Junjie,Lin, Zhouchen,Shan, Shiguang,&Luo, Zhongxuan.(2016).Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,38(12),2457-2471.
MLA	Liu, Risheng,et al."Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 38.12(2016):2457-2471.