Welcome to the InfoSci Platform
Reference Hub1
A Selective Sparse Coding Model with Embedded Attention Mechanism

A Selective Sparse Coding Model with Embedded Attention Mechanism

Qingyong Li, Zhiping Shi, Zhongzhi Shi
Copyright: © 2007 |Volume: 1 |Issue: 4 |Pages: 14
ISSN: 1557-3958|EISSN: 1557-3966|ISSN: 1557-3958|EISBN13: 9781615201969|EISSN: 1557-3966|DOI: 10.4018/jcini.2007100105
Cite Article Cite Article

MLA

Li, Qingyong, et al. "A Selective Sparse Coding Model with Embedded Attention Mechanism." IJCINI vol.1, no.4 2007: pp.61-74. http://doi.org/10.4018/jcini.2007100105

APA

Li, Q., Shi, Z., & Shi, Z. (2007). A Selective Sparse Coding Model with Embedded Attention Mechanism. International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 1(4), 61-74. http://doi.org/10.4018/jcini.2007100105

Chicago

Li, Qingyong, Zhiping Shi, and Zhongzhi Shi. "A Selective Sparse Coding Model with Embedded Attention Mechanism," International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) 1, no.4: 61-74. http://doi.org/10.4018/jcini.2007100105

Export Reference

Mendeley
Favorite Full-Issue Download

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.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.