Multiview, Few-Labeled Object Categorization by Predicting Labels With View Consistency
文献类型：期刊论文
| 作者 | Zhang, Chunjie1,2 ; Cheng, Jian3,4,5; Tian, Qi6
|
| 刊名 | IEEE TRANSACTIONS ON CYBERNETICS
 |
| 出版日期 | 2019-11-01 |
| 卷号 | 49期号:11页码:3834-3843 |
| 关键词 | Few-labeled images multiview classification object categorization view consistency |
| ISSN号 | 2168-2267 |
| DOI | 10.1109/TCYB.2018.2845912 |
| 通讯作者 | Zhang, Chunjie(chunjie.zhang@ia.ac.cn) |
| 英文摘要 | The categorization accuracies of objects have been greatly improved in recent years. However, large quantities of labeled images are needed. many methods fail when only few labeled images are available. To tackle the few-labeled object categorization problem, we need to represent and classify them from multiple views. In this paper, we propose a novel multiview, few-labeled object categorization algorithm by predicting the labels of images with view consistency (MVFL-VC). We use labeled images along with other unlabeled images in a unified framework. A mapping function is learned to model the correlations of images with their labels. Since there are no labeling information for unlabeled images, we simultaneously learn the mapping function and image labels by classification error minimization. We make use of multiview information for joint object categorization. Although different views represent different aspects of images, for one image, the predicted categories of multiple views should be consistent with each other. We learn the mapping function by minimizing the summed classification losses along with the discrepancy of predicted labels between different views in an alternative way. We conduct object categorization experiments on five public image datasets and compare with other semi-supervised methods. Experimental results well demonstrate the effectiveness of the proposed MVFL-VC method. |
| WOS关键词 | CONSTRAINED LOW-RANK ; IMAGE CLASSIFICATION ; REPRESENTATION ; PROPAGATION ; FRAMEWORK ; FEATURES |
| 资助项目 | Scientific Research Key Program of Beijing Municipal Commission of Education[KZ201610005012] ; National Science Foundation of China[61429201] ; ARO[W911NF-15-1-0290] ; NEC Laboratories of America ; Blippar |
| WOS研究方向 | Automation & Control Systems ; Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000476811000001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | Scientific Research Key Program of Beijing Municipal Commission of Education ; National Science Foundation of China ; ARO ; NEC Laboratories of America ; Blippar |
| 源URL | [http://ir.ia.ac.cn/handle/173211/27806]  |
| 专题 | 类脑芯片与系统研究 |
| 通讯作者 | Zhang, Chunjie |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 5.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China 6.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA |
| 推荐引用方式 GB/T 7714 | Zhang, Chunjie,Cheng, Jian,Tian, Qi. Multiview, Few-Labeled Object Categorization by Predicting Labels With View Consistency[J]. IEEE TRANSACTIONS ON CYBERNETICS,2019,49(11):3834-3843. |
| APA | Zhang, Chunjie,Cheng, Jian,&Tian, Qi.(2019).Multiview, Few-Labeled Object Categorization by Predicting Labels With View Consistency.IEEE TRANSACTIONS ON CYBERNETICS,49(11),3834-3843. |
| MLA | Zhang, Chunjie,et al."Multiview, Few-Labeled Object Categorization by Predicting Labels With View Consistency".IEEE TRANSACTIONS ON CYBERNETICS 49.11(2019):3834-3843. |
入库方式： OAI收割
来源：自动化研究所
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。