A Selective Sparse Coding Model with Embedded Attention Mechanism

Qingyong Li, Zhiping Shi and Zhongzhi Shi
Additional contact information
Qingyong Li: Beijing Jiaotong University, China
Zhiping Shi: Chinese Academy of Sciences, China
Zhongzhi Shi: Chinese Academy of Sciences, China

International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 2007, vol. 1, issue 4, 61-74

Abstract: Sparse coding theory demonstrates that the neurons in primary visual cortex form a sparse representation of natural scenes in the viewpoint of statistics, but a typical scene contains many different patterns (corresponding to neurons in cortex) competing for neural representation because of the limited processing capacity of the visual system. We propose an attention-guided sparse coding model (AGSC). This model includes two modules: non-uniform sampling module simulating the process of retina and data-driven attention module based on the response saliency (RS). Our experiment results show that the model notably decreases the number of coefficients that may be activated and retains the main vision information at the same time. It provides a way to improve the coding efficiency for sparse coding model and to achieve good performance in both population sparseness and lifetime sparseness.

Date: 2007
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 018/jcini.2007100105 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jcini0:v:1:y:2007:i:4:p:61-74

Access Statistics for this article

International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) is currently edited by Kangshun Li

More articles in International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) from IGI Global
Bibliographic data for series maintained by Journal Editor ().