Deep and Structured Robust Information Theoretic Learning for Image Analysis

doi:10.1109/TIP.2016.2588330

	Deep and Structured Robust Information Theoretic Learning for Image Analysis
	Deng, Yue 1,2; Bao, Feng 1; Deng, Xuesong 3; Wang, Ruiping 3; Kong, Youyong 4; Dai, Qionghai 1
	2016-09-01
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	25 期号:9 页码:4209-4221
摘要	This paper presents a robust information theoretic (RIT) model to reduce the uncertainties, i.e., missing and noisy labels, in general discriminative data representation tasks. The fundamental pursuit of our model is to simultaneously learn a transformation function and a discriminative classifier that maximize the mutual information of data and their labels in the latent space. In this general paradigm, we, respectively, discuss three types of the RIT implementations with linear subspace embedding, deep transformation, and structured sparse learning. In practice, the RIT and deep RIT are exploited to solve the image categorization task whose performances will be verified on various benchmark data sets. The structured sparse RIT is further applied to a medical image analysis task for brain magnetic resonance image segmentation that allows group-level feature selections on the brain tissues.
关键词	Data embedding mutual information deep learning structured-sparse learning image classification brain MRI segmentation
DOI	10.1109/TIP.2016.2588330
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61327902] ; National Natural Science Foundation of China[61120106003] ; National Natural Science Foundation of China[61379083] ; National Science Foundation of Jiangsu Province, China[BK20150650]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000380355600005
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：23[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/2XEOYT63/8250
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Deng, Yue
作者单位	1.Tsinghua Univ, Automat Dept, Tsinghua Natl Lab Informat Sci & Technol, Beijing 100084, Peoples R China 2.Univ Calif San Francisco, San Francisco Med Ctr, San Francisco, CA 94158 USA 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 4.Southeast Univ, Sch Comp Sci & Engn, Nanjing 210000, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Deng, Yue,Bao, Feng,Deng, Xuesong,et al. Deep and Structured Robust Information Theoretic Learning for Image Analysis[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2016,25(9):4209-4221.
APA	Deng, Yue,Bao, Feng,Deng, Xuesong,Wang, Ruiping,Kong, Youyong,&Dai, Qionghai.(2016).Deep and Structured Robust Information Theoretic Learning for Image Analysis.IEEE TRANSACTIONS ON IMAGE PROCESSING,25(9),4209-4221.
MLA	Deng, Yue,et al."Deep and Structured Robust Information Theoretic Learning for Image Analysis".IEEE TRANSACTIONS ON IMAGE PROCESSING 25.9(2016):4209-4221.