Manifold Preserving: An Intrinsic Approach for Semisupervised Distance Metric Learning

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	Manifold Preserving: An Intrinsic Approach for Semisupervised Distance Metric Learning
	Shihui Ying; Zhijie Wen; Jun Shi; Yaxin Peng; Jigen Peng; Hong Qiao
发表期刊	IEEE Transactions on Neural Networks and Learning Systems
	2017
卷号	PP 期号:99 页码:1-12
摘要	In this paper, we address the semisupervised distance metric learning problem and its applications in classification and image retrieval. First, we formulate a semisupervised distance metric learning model by considering the metric information of inner classes and interclasses. In this model, an adaptive parameter is designed to balance the inner metrics and intermetrics by using data structure. Second, we convert the model to a minimization problem whose variable is symmetric positive-definite matrix. Third, in implementation, we deduce an intrinsic steepest descent method, which assures that the metric matrix is strictly symmetric positive-definite at each iteration, with the manifold structure of the symmetric positivedefinite matrix manifold. Finally, we test the proposed algorithm on conventional data sets, and compare it with other four representative methods. The numerical results validate that the proposed method significantly improves the classification with the same computational efficiency.
关键词	Classification Distance Metric Learning Intrinsic Algorithm Matrix Manifold Semisupervised Learning.
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/20103
专题	多模态人工智能系统全国重点实验室_机器人理论与应用
推荐引用方式 GB/T 7714	Shihui Ying,Zhijie Wen,Jun Shi,et al. Manifold Preserving: An Intrinsic Approach for Semisupervised Distance Metric Learning[J]. IEEE Transactions on Neural Networks and Learning Systems,2017,PP(99):1-12.
APA	Shihui Ying,Zhijie Wen,Jun Shi,Yaxin Peng,Jigen Peng,&Hong Qiao.(2017).Manifold Preserving: An Intrinsic Approach for Semisupervised Distance Metric Learning.IEEE Transactions on Neural Networks and Learning Systems,PP(99),1-12.
MLA	Shihui Ying,et al."Manifold Preserving: An Intrinsic Approach for Semisupervised Distance Metric Learning".IEEE Transactions on Neural Networks and Learning Systems PP.99(2017):1-12.

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
Manifold Preserving （3665KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览