CASIA OpenIR  > 智能感知与计算研究中心
Exploring the Power of Kernel in Feature Representation for Object Categorization
Weiqiang Ren; Yinan Yu; Junge Zhang; Kaiqi Huang
2013
Conference NameInternational Conference on Neural Information Processing
Source PublicationInternational Conference on Neural Information Processing
Pages541-548
Conference DateNovember  2013
Conference PlaceDaegu, Korea
AbstractLearning robust and invariant feature representations is always a crucial task in visual recognition and analysis. Mean square error (MSE) has been used in many feature encoding methods as a feature reconstruction criterion. However, due to the non-Gaussian noises and non-linearity structures in natural images, second order statistics like MSE are usually not sufficient to capture these information from image data. In this paper, motivated by the information-theoretic learning framework and kernel machine learning, we adopt a similarity measure called correntropy in the auto-encoder model to tackle this problem. The proposed maximum correntropy auto-encoder (MCAE) learns more robust and discriminative representations than MSE based model by performing computation in an infinite dimensional kernel space. Moreover, we further exploit the power of kernel by learning a kernel embedding neural network which explicitly maps data from Euclidean space to an approximated kernel space. Experimental results on standard object categorization datasets show the effectiveness of kernel learning in feature representation for visual recognition task.
KeywordAuto Encoder   maximum Correntropy   explicit Kernel Embedding
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12686
Collection智能感知与计算研究中心
Corresponding AuthorKaiqi Huang
Affiliation中国科学院自动化研究所
Recommended Citation
GB/T 7714
Weiqiang Ren,Yinan Yu,Junge Zhang,et al. Exploring the Power of Kernel in Feature Representation for Object Categorization[C],2013:541-548.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Weiqiang Ren]'s Articles
[Yinan Yu]'s Articles
[Junge Zhang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Weiqiang Ren]'s Articles
[Yinan Yu]'s Articles
[Junge Zhang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Weiqiang Ren]'s Articles
[Yinan Yu]'s Articles
[Junge Zhang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.