論文

査読有り
2006年12月

A neural network implementation of a saliency map model

NEURAL NETWORKS
  • Matthew de Brecht
  • ,
  • Jun Saiki

19
10
開始ページ
1467
終了ページ
1474
記述言語
英語
掲載種別
研究論文(学術雑誌)
DOI
10.1016/j.neunet.2005.12.004
出版者・発行元
PERGAMON-ELSEVIER SCIENCE LTD

The saliency map model proposed by Itti and Koch [Itti, L., & Koch, C. (2000). A saliency-based search mechanism for overt and covert shifts of visual attention. Vision Research, 40, 1489-1506] has been a popular model for explaining the guidance of visual attention using only bottom-up information. In this paper we expand Itti and Koch's model and propose how it could be implemented by neural networks with biologically realistic dynamics. In particular, we show that by incorporating synaptic depression into the model, network activity can be normalized and competition within the feature maps can be regulated in a biologically plausible manner. Furthermore, the dynamical nature of our model permits further analysis of the time course of saliency computation, and also allows the model to calculate saliency for dynamic visual scenes. In addition to explaining the high saliency of pop-out targets in visual search tasks, our model explains attentional grab by sudden-onset stimuli, which was not accounted for by previous models. (c) 2006 Elsevier Ltd. All rights reserved.

Web of Science ® 被引用回数 : 19

リンク情報
DOI
https://doi.org/10.1016/j.neunet.2005.12.004
Web of Science
https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000243215200002&DestApp=WOS_CPL
ID情報
  • DOI : 10.1016/j.neunet.2005.12.004
  • ISSN : 0893-6080
  • eISSN : 1879-2782
  • Web of Science ID : WOS:000243215200002

エクスポート
BibTeX RIS