Weakly Supervised Multilabel Clustering and its Applications in Computer Vision

CORC > 西安光学精密机械研究所 > 中国科学院西安光学精密机械研究所 > 光学影像学习与分析中心

	Weakly Supervised Multilabel Clustering and its Applications in Computer Vision
	Xia, Yingjie 1; Nie, Liqiang 2; Zhang, Luming 3; Yang, Yi 4; Hong, Richang 3; Li, Xuelong 5
刊名	ieee transactions on cybernetics
	2016-12-01
卷号	46 期号:12 页码:3220-3232
关键词	Annealing clustering computer vision multilabel semantic weakly supervised
ISSN号	2168-2267
通讯作者	xia, yj (reprint author), zhejiang univ, coll comp sci, hangzhou 310027, zhejiang, peoples r china.
产权排序	5
英文摘要	clustering is a useful statistical tool in computer vision and machine learning. it is generally accepted that introducing supervised information brings remarkable performance improvement to clustering. however, assigning accurate labels is expensive when the amount of training data is huge. existing supervised clustering methods handle this problem by transferring the bag-level labels into the instance-level descriptors. however, the assumption that each bag has a single label limits the application scope seriously. in this paper, we propose weakly supervised multilabel clustering, which allows assigning multiple labels to a bag. based on this, the instance-level descriptors can be clustered with the guidance of bag-level labels. the key technique is a weakly supervised random forest that infers the model parameters. thereby, a deterministic annealing strategy is developed to optimize the nonconvex objective function. the proposed algorithm is efficient in both the training and the testing stages. we apply it to three popular computer vision tasks: 1) image clustering; 2) semantic image segmentation; and 3) multiple objects localization. impressive performance on the state-of-the-art image data sets is achieved in our experiments.
学科主题	computer science, artificial intelligence ; computer science, cybernetics
WOS标题词	science & technology ; technology
类目[WOS]	computer science, artificial intelligence ; computer science, cybernetics
研究领域[WOS]	computer science
关键词[WOS]	image segmentation ; action recognition ; classification ; scale
收录类别	SCI
语种	英语
WOS记录号	WOS:000388923100043
内容类型	期刊论文
源URL	[http://ir.opt.ac.cn/handle/181661/28560]
专题	西安光学精密机械研究所_光学影像学习与分析中心
作者单位	1.Zhejiang Univ, Coll Comp Sci, Hangzhou 310027, Zhejiang, Peoples R China 2.Shandong Univ, Sch Comp Sci & Technol, Jinan 250100, Peoples R China 3.Hefei Univ Technol, Dept Comp Sci & Informat Engn, Hefei 230009, Peoples R China 4.Univ Technol Sydney, Ctr Quantum Computat & Intelligent Syst, Ultimo, NSW 123, Australia 5.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr OPTical IMagery Anal & Learning, Xian 710119, Peoples R China
推荐引用方式 GB/T 7714	Xia, Yingjie,Nie, Liqiang,Zhang, Luming,et al. Weakly Supervised Multilabel Clustering and its Applications in Computer Vision[J]. ieee transactions on cybernetics,2016,46(12):3220-3232.
APA	Xia, Yingjie,Nie, Liqiang,Zhang, Luming,Yang, Yi,Hong, Richang,&Li, Xuelong.(2016).Weakly Supervised Multilabel Clustering and its Applications in Computer Vision.ieee transactions on cybernetics,46(12),3220-3232.
MLA	Xia, Yingjie,et al."Weakly Supervised Multilabel Clustering and its Applications in Computer Vision".ieee transactions on cybernetics 46.12(2016):3220-3232.