Knowledge Commons of Institute of Automation,CAS
Fine-Grained Image Classification via Low-Rank Sparse Coding With General and Class-Specific Codebooks | |
Zhang, Chunjie1,2,3; Liang, Chao4; Li, Liang2,3; Liu, Jing5; Huang, Qingming2,3,6; Tian, Qi7 | |
发表期刊 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS |
2017-07-01 | |
卷号 | 28期号:7页码:1550-1559 |
文章类型 | Article |
摘要 | This paper tries to separate fine-grained images by jointly learning the encoding parameters and codebooks through low-rank sparse coding (LRSC) with general and class-specific codebook generation. Instead of treating each local feature independently, we encode the local features within a spatial region jointly by LRSC. This ensures that the spatially nearby local features with similar visual characters are encoded by correlated parameters. In this way, we can make the encoded parameters more consistent for fine-grained image representation. Besides, we also learn a general codebook and a number of class-specific codebooks in combination with the encoding scheme. Since images of fine-grained classes are visually similar, the difference is relatively small between the general codebook and each class-specific codebook. We impose sparsity constraints to model this relationship. Moreover, the incoherences with different codebooks and class-specific codebooks are jointly considered. We evaluate the proposed method on several public image data sets. The experimental results show that by learning general and classspecific codebooks with the joint encoding of local features, we are able to model the differences among different fine-grained classes than many other fine-grained image classification methods. |
关键词 | Fine Grained Image Representation Semantic Space Visual Recognition |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1109/TNNLS.2016.2545112 |
关键词[WOS] | FEATURES ; CATEGORIZATION ; DICTIONARY ; KERNEL ; RECOGNITION ; FORESTS ; SEARCH |
收录类别 | SCI |
语种 | 英语 |
项目资助者 | Open Project of Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences ; National Basic Research Program of China(2012CB316400 ; National Natural Science Foundation of China(61272329 ; 2015CB351802) ; 61303114 ; 61303154 ; 61332016 ; 61402431) |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000404048300006 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/15235 |
专题 | 紫东太初大模型研究中心_图像与视频分析 |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing 100190, Peoples R China 4.Wuhan Univ, Sch Comp, Natl Engn Res Ctr Multimedia Software, Wuhan 430072, Peoples R China 5.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 6.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 7.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhang, Chunjie,Liang, Chao,Li, Liang,et al. Fine-Grained Image Classification via Low-Rank Sparse Coding With General and Class-Specific Codebooks[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2017,28(7):1550-1559. |
APA | Zhang, Chunjie,Liang, Chao,Li, Liang,Liu, Jing,Huang, Qingming,&Tian, Qi.(2017).Fine-Grained Image Classification via Low-Rank Sparse Coding With General and Class-Specific Codebooks.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,28(7),1550-1559. |
MLA | Zhang, Chunjie,et al."Fine-Grained Image Classification via Low-Rank Sparse Coding With General and Class-Specific Codebooks".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 28.7(2017):1550-1559. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
07448920.pdf(1901KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 |
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。
修改评论