Local margin based semi-supervised discriminant embedding for visual recognition

被引:13
作者
Pan, Feng [2 ,3 ]
Wang, Jiandong [2 ]
Lin, Xiaohui [1 ,4 ]
机构
[1] Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing 100088, Peoples R China
[2] Nanjing Univ Aeronaut & Astronaut, Coll Informat Sci & Technol, Nanjing 210016, Peoples R China
[3] Shenzhen Univ, Coll Management, Shenzhen 518060, Guangdong, Peoples R China
[4] Shenzhen Univ, Coll Informat Engineer, Shenzhen 518060, Guangdong, Peoples R China
关键词
Dimensionality reduction; Margin; Manifold learning; Semi-supervised learning; NONLINEAR DIMENSIONALITY REDUCTION; FRAMEWORK;
D O I
10.1016/j.neucom.2010.11.004
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Most manifold learning algorithms adopt the k nearest neighbors function to construct the adjacency graph. However, severe bias may be introduced in this case if the samples are not uniformly distributed in the ambient space. In this paper a semi-supervised dimensionality reduction method is proposed to alleviate this problem. Based on the notion of local margin, we simultaneously maximize the separability between different classes and estimate the intrinsic geometric structure of the data by both the labeled and unlabeled samples. For high-dimensional data, a discriminant subspace is derived via maximizing the cumulative local margins. Experimental results on high-dimensional classification tasks demonstrate the efficacy of our algorithm. (C) 2010 Elsevier B.V. All rights reserved.
引用
收藏
页码:812 / 819
页数:8
相关论文
共 23 条
  • [1] [Anonymous], 2002, Principal components analysis
  • [2] [Anonymous], 2003, ADV NEURAL INFORM PR
  • [3] Cai D., 2007, PROC IEEE 11 INT C C
  • [4] Cevikalp H., 2008, Computer Vision and Pattern Recognition, IEEE Conference on, P1
  • [5] A unified semi-supervised dimensionality reduction framework for manifold learning
    Chatpatanasiri, Ratthachat
    Kijsirikul, Boonserm
    [J]. NEUROCOMPUTING, 2010, 73 (10-12) : 1631 - 1640
  • [6] Chen J., 2007, IEEE C COMPUTER VISI
  • [7] Gilad-Bachrach R., 2004, PROC 21 INT C MACH L, P43
  • [8] Golub G. H., 1996, MATRIX COMPUTATIONS
  • [9] Face recognition using Laplacianfaces
    He, XF
    Yan, SC
    Hu, YX
    Niyogi, P
    Zhang, HJ
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2005, 27 (03) : 328 - 340
  • [10] Keinosuke Fukunaga, 1972, Introduction to Statistical Pattern Recognition