中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Multi-Level Discriminative Dictionary Learning With Application to Large Scale Image Classification

文献类型:期刊论文

作者Shen, Li2; Sun, Gang2,3; Huang, Qingming2,4; Wang, Shuhui4; Lin, Zhouchen1; Wu, Enhua3,5
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2015-10-01
卷号24期号:10页码:3109-3123
关键词Sparse coding discriminative dictionary learning hierarchical method large scale classification
ISSN号1057-7149
DOI10.1109/TIP.2015.2438548
英文摘要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.
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
语种英语
WOS记录号WOS:000356539800001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/9658]  
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.Peking Univ, Key Lab Machine Percept, Sch Elect Engn & Comp Sci, Minist Educ, Beijing 100871, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Chinese Acad Sci, State Key Lab Comp Sci, Inst Software, Beijing 100190, Peoples R China
4.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, 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.

入库方式: OAI收割

来源:计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。