Semi-supervised discriminant analysis via spectral transduction | |
Zhai, Deming ; Chang, Hong ; Li, Bo ; Shan, Shiguang ; Chen, Xilin ; Gao, Wen | |
2009 | |
英文摘要 | Linear Discriminant Analysis (LDA) is a popular method for dimensionality reduction and classification. In real-world applications when there is no sufficient labeled data, LDA suffers from serious performance drop or even fails to work. In this paper, we propose a novel method called Spectral Transduction Semi-Supervised Discriminant Analysis (STSDA), which can alleviate such problem by utilizing both labeled and unla-beled data. Our method takes into consideration both label augmenting and local structure preserving. First, we formulate label transduction with labeled and unlabeled data as a constrained convex optimization problem and solve it efficiently with a closed-form solution by using orthogonal projector matrices. Then, unlabeled data with reliable class estimations are selected with a balanced strategy to augment the original labeled data set. At last, LDA with manifold regularization is performed. Experimental results on face recognition demonstrate the effectiveness of our proposed method. ? 2009. The copyright of this document resides with its authors.; EI; 0 |
语种 | 英语 |
DOI标识 | 10.5244/C.23.32 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/411267] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Zhai, Deming,Chang, Hong,Li, Bo,et al. Semi-supervised discriminant analysis via spectral transduction. 2009-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论