Unsupervised and Semi-Supervised Image Classification With Weak Semantic Consistency

doi:10.1109/TMM.2019.2903628

	Unsupervised and Semi-Supervised Image Classification With Weak Semantic Consistency
	Zhang, Chunjie1 ; Cheng, Jian2,3 ; Tian, Qi 4
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
	2019-10-01
卷号	21 期号:10 页码:2482-2491
通讯作者	Zhang, Chunjie(chunjie.zhang@ia.ac.cn)
摘要	Supervised methods have been widely used for image classifications. Although great progress has been made, existing supervised methods rely on well-labeled samples for classification. However, we often have large quantities of images with few or no labels. To cope with this problem, in this paper, we propose a novel weak semantic consistency constrained image classification method. We start from an extreme circumstance by viewing each image as one class. We train exemplar classifiers to separate each image from other images. For each image, we use the learned exemplar classifiers to predict the weak semantic correlations with the exemplar classifiers. When no labeled information is available, we cluster images using the weak semantic correlations and assign images within one cluster to the same mid-level class. When partially labeled images are available, we can use them to constrain the clustering process by assigning images of varied semantics to different mid-level classes. We use the newly assigned images for classifier training and new image representations, which can then be used for similar image assignments. The classifier training, image representation, and assignment processes are repeated until convergence. We conduct both unsupervised and semi-supervised image classification experiments on several datasets. The experimental results show the effectiveness of the proposed unsupervised and semi-supervised weak semantic consistency image classification method.
关键词	Semi-supervised classification unsupervised classification weak semantic representation semantic consistency
DOI	10.1109/TMM.2019.2903628
关键词[WOS]	LABEL PROPAGATION ; LOW-RANK ; REPRESENTATION
收录类别	SCI
语种	英语
资助项目	National Science Foundation of China[61872362] ; National Science Foundation of China[61876135] ; National Science Foundation of China[61872362] ; National Science Foundation of China[61876135]
项目资助者	National Science Foundation of China
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:000489728400005
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	图像视频处理与分析
引用统计	被引频次：34[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/26667
专题	复杂系统认知与决策实验室_高效智能计算与学习
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.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China 4.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
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Zhang, Chunjie,Cheng, Jian,Tian, Qi. Unsupervised and Semi-Supervised Image Classification With Weak Semantic Consistency[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2019,21(10):2482-2491.
APA	Zhang, Chunjie,Cheng, Jian,&Tian, Qi.(2019).Unsupervised and Semi-Supervised Image Classification With Weak Semantic Consistency.IEEE TRANSACTIONS ON MULTIMEDIA,21(10),2482-2491.
MLA	Zhang, Chunjie,et al."Unsupervised and Semi-Supervised Image Classification With Weak Semantic Consistency".IEEE TRANSACTIONS ON MULTIMEDIA 21.10(2019):2482-2491.