Multiple Cayley-Klein metric learning

doi:10.1371/journal.pone.0184865

	Multiple Cayley-Klein metric learning
	Bi, Yanhong1,2 ; Fan, Bin1 ; Wu, Fuchao1 ; Bin Fan
发表期刊	PLOS ONE
	2017-09-21
卷号	12 期号:9 页码:1-15
文章类型	Article
摘要	As a specific kind of non-Euclidean metric lies in projective space, Cayley-Klein metric has been recently introduced in metric learning to deal with the complex data distributions in computer vision tasks. In this paper, we extend the original Cayley-Klein metric to the multiple Cayley-Klein metric, which is defined as a linear combination of several Cayley-Klein metrics. Since Cayley-Klein is a kind of non-linear metric, its combination could model the data space better, thus lead to an improved performance. We show how to learn a multiple Cayley-Klein metric by iterative optimization over single Cayley-Klein metric and their combination coefficients under the objective to maximize the performance on separating interclass instances and gathering intra-class instances. Our experiments on several benchmarks are quite encouraging.
关键词	Metric Learning Cayley-klein Metric
WOS标题词	Science & Technology
DOI	10.1371/journal.pone.0184865
关键词[WOS]	NEAREST-NEIGHBOR CLASSIFICATION ; VERIFICATION
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61375043 ; 61472119 ; 61672032)
WOS研究方向	Science & Technology - Other Topics
WOS类目	Multidisciplinary Sciences
WOS记录号	WOS:000411339900053
引用统计	被引频次：1[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/173211/19695
专题	多模态人工智能系统全国重点实验室_机器人视觉
通讯作者	Bin Fan
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Bi, Yanhong,Fan, Bin,Wu, Fuchao,et al. Multiple Cayley-Klein metric learning[J]. PLOS ONE,2017,12(9):1-15.
APA	Bi, Yanhong,Fan, Bin,Wu, Fuchao,&Bin Fan.(2017).Multiple Cayley-Klein metric learning.PLOS ONE,12(9),1-15.
MLA	Bi, Yanhong,et al."Multiple Cayley-Klein metric learning".PLOS ONE 12.9(2017):1-15.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
PLOS-ONE-2017.pdf（2897KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载