Multi-Level Discriminative Dictionary Learning With Application to Large Scale Image Classification

doi:10.1109/TIP.2015.2438548

	Multi-Level Discriminative Dictionary Learning With Application to Large Scale Image Classification
	Shen, Li 1; Sun, Gang 1,2; Huang, Qingming 1,3; Wang, Shuhui 3; Lin, Zhouchen 4; Wu, Enhua 2,5
	2015-10-01
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	24 期号:10 页码:3109-3123
摘要	The sparse coding technique has shown flexibility and capability in image representation and analysis. It is a powerful tool in many visual applications. Some recent work has shown that incorporating the properties of task (such as discrimination for classification task) into dictionary learning is effective for improving the accuracy. However, the traditional supervised dictionary learning methods suffer from high computation complexity when dealing with large number of categories, making them less satisfactory in large scale applications. In this paper, we propose a novel multi-level discriminative dictionary learning method and apply it to large scale image classification. Our method takes advantage of hierarchical category correlation to encode multi-level discriminative information. Each internal node of the category hierarchy is associated with a discriminative dictionary and a classification model. The dictionaries at different layers are learnt to capture the information of different scales. Moreover, each node at lower layers also inherits the dictionary of its parent, so that the categories at lower layers can be described with multi-scale information. The learning of dictionaries and associated classification models is jointly conducted by minimizing an overall tree loss. The experimental results on challenging data sets demonstrate that our approach achieves excellent accuracy and competitive computation cost compared with other sparse coding methods for large scale image classification.
关键词	Sparse coding discriminative dictionary learning hierarchical method large scale classification
DOI	10.1109/TIP.2015.2438548
收录类别	SCI
语种	英语
资助项目	National Basic Research Program of China (973 Program)[2012CB316400] ; National Natural Science Foundation (NSF) of China[61332016] ; National Natural Science Foundation (NSF) of China[61025011] ; National Natural Science Foundation (NSF) of China[61303160] ; National Natural Science Foundation (NSF) of China[61272326] ; University of Macau[MYRG202(Y1-L4)-FST11-WEH] ; 973 Program of China[2015CB352502] ; NSF of China[61272341] ; NSF of China[61231002] ; 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:000356539800001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：43[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/2XEOYT63/9659
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Lin, Zhouchen
作者单位	1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, State Key Lab Comp Sci, Inst Software, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 4.Peking Univ, Key Lab Machine Percept, Sch Elect Engn & Comp Sci, Minist Educ, Beijing 100871, Peoples R China 5.Univ Macau, Macau 999078, Peoples R China
推荐引用方式 GB/T 7714	Shen, Li,Sun, Gang,Huang, Qingming,et al. Multi-Level Discriminative Dictionary Learning With Application to Large Scale Image Classification[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2015,24(10):3109-3123.
APA	Shen, Li,Sun, Gang,Huang, Qingming,Wang, Shuhui,Lin, Zhouchen,&Wu, Enhua.(2015).Multi-Level Discriminative Dictionary Learning With Application to Large Scale Image Classification.IEEE TRANSACTIONS ON IMAGE PROCESSING,24(10),3109-3123.
MLA	Shen, Li,et al."Multi-Level Discriminative Dictionary Learning With Application to Large Scale Image Classification".IEEE TRANSACTIONS ON IMAGE PROCESSING 24.10(2015):3109-3123.