Variational Bayesian Learning for Dirichlet Process Mixture of Inverted Dirichlet Distributions in Non-Gaussian Image Feature Modeling

doi:10.1109/TNNLS.2018.2844399

	Variational Bayesian Learning for Dirichlet Process Mixture of Inverted Dirichlet Distributions in Non-Gaussian Image Feature Modeling
	Ma, Zhanyu 1; Lai, Yuping 2; Kleijn, W. Bastiaan 3; Song, Yi-Zhe 4; Wang, Liang5 ; Guo, Jun 1
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2019-02-01
卷号	30 期号:2 页码:449-463
关键词	Bayesian estimation computer vision Dirichlet process (DP) mixture inverted Dirichlet distribution variational learning
ISSN号	2162-237X
DOI	10.1109/TNNLS.2018.2844399
通讯作者	Ma, Zhanyu(mazhanyu@bupt.edu.cn)
英文摘要	In this paper, we develop a novel variational Bayesian learning method for the Dirichlet process (DP) mixture of the inverted Dirichlet distributions, which has been shown to be very flexible for modeling vectors with positive elements. The recently proposed extended variational inference (EVI) framework is adopted to derive an analytically tractable solution. The convergency of the proposed algorithm is theoretically guaranteed by introducing single lower bound approximation to the original objective function in the EVI framework. In principle, the proposed model can be viewed as an infinite inverted Dirichlet mixture model that allows the automatic determination of the number of mixture components from data. Therefore, the problem of predetermining the optimal number of mixing components has been overcome. Moreover, the problems of overfitting and underfitting are avoided by the Bayesian estimation approach. Compared with several recently proposed DP-related methods and conventional applied methods, the good performance and effectiveness of the proposed method have been demonstrated with both synthesized data and real data evaluations.
资助项目	National Key Research and Development Program of China[2016YFB1001000] ; National Natural Science Foundation of China[61773071] ; Beijing Nova Program[Z171100001117049] ; Beijing Nova Program Interdisciplinary Cooperation[Z181100006218137] ; Beijing Natural Science Foundation[4162044] ; Beijing Natural Science Foundation[KZ201810009011] ; Beijing Education Commission[KZ201810009011]
WOS关键词	PARALLEL FRAMEWORK ; TEXT DETECTION ; SELECTION ; CHANNELS ; VIDEO ; TIME
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:000457114600010
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Beijing Nova Program ; Beijing Nova Program Interdisciplinary Cooperation ; Beijing Natural Science Foundation ; Beijing Education Commission
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/25325]
专题	中国科学院自动化研究所
通讯作者	Ma, Zhanyu
作者单位	1.Beijing Univ Posts & Telecommun, Pattern Recognit & Intelligent Syst Lab, Beijing 100876, Peoples R China 2.North China Univ Technol, Dept Informat Secur, Beijing 100144, Peoples R China 3.Victoria Univ Wellington, Commun & Signal Proc Grp, Wellington 6140, New Zealand 4.Queen Mary Univ London, Sch Elect Engn & Comp Sci, SketchX Lab, London E1 4NS, England 5.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Ma, Zhanyu,Lai, Yuping,Kleijn, W. Bastiaan,et al. Variational Bayesian Learning for Dirichlet Process Mixture of Inverted Dirichlet Distributions in Non-Gaussian Image Feature Modeling[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2019,30(2):449-463.
APA	Ma, Zhanyu,Lai, Yuping,Kleijn, W. Bastiaan,Song, Yi-Zhe,Wang, Liang,&Guo, Jun.(2019).Variational Bayesian Learning for Dirichlet Process Mixture of Inverted Dirichlet Distributions in Non-Gaussian Image Feature Modeling.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,30(2),449-463.
MLA	Ma, Zhanyu,et al."Variational Bayesian Learning for Dirichlet Process Mixture of Inverted Dirichlet Distributions in Non-Gaussian Image Feature Modeling".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 30.2(2019):449-463.