A neural computational model for bottom-up attention with invariant and overcomplete representation

BACKGROUND: An important problem in selective attention is determining the ways the primary visual cortex contributes to the encoding of bottom-up saliency and the types of neural computation that are effective to model this process. To address this problem, we constructed a two-layered network that...

Descripción completa

Detalles Bibliográficos
Autores principales: Qi, Zou, Songnian, Zhao, Zhe, Wang, Yaping, Huang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2012
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3599588/
https://www.ncbi.nlm.nih.gov/pubmed/23190754
http://dx.doi.org/10.1186/1471-2202-13-145
_version_ 1782262997525200896
author Qi, Zou
Songnian, Zhao
Zhe, Wang
Yaping, Huang
author_facet Qi, Zou
Songnian, Zhao
Zhe, Wang
Yaping, Huang
author_sort Qi, Zou
collection PubMed
description BACKGROUND: An important problem in selective attention is determining the ways the primary visual cortex contributes to the encoding of bottom-up saliency and the types of neural computation that are effective to model this process. To address this problem, we constructed a two-layered network that satisfies the neurobiological constraints of the primary visual cortex to detect salient objects. We carried out experiments on both synthetic images and natural images to explore the influences of different factors, such as network structure, the size of each layer, the type of suppression and the combination strategy, on saliency detection performance. RESULTS: The experimental results statistically demonstrated that the type and scale of filters contribute greatly to the encoding of bottom-up saliency. These two factors correspond to the mechanisms of invariant encoding and overcomplete representation in the primary visual cortex. CONCLUSIONS: (1) Instead of constructing Gabor functions or Gaussian pyramids filters for feature extraction as traditional attention models do, we learn overcomplete basis sets from natural images to extract features for saliency detection. Experiments show that given the proper layer size and a robust combination strategy, the learned overcomplete basis set outperforms a complete set and Gabor pyramids in visual saliency detection. This finding can potentially be applied in task-dependent and supervised object detection. (2) A hierarchical coding model that can represent invariant features, is designed for the pre-attentive stage of bottom-up attention. This coding model improves robustness to noises and distractions and improves the ability of detecting salient structures, such as collinear and co-circular structures, and several composite stimuli. This result indicates that invariant representation contributes to saliency detection (popping out) in bottom-up attention. The aforementioned perspectives will significantly contribute to the in-depth understanding of the information processing mechanism in the primary visual system.
format Online
Article
Text
id pubmed-3599588
institution National Center for Biotechnology Information
language English
publishDate 2012
publisher BioMed Central
record_format MEDLINE/PubMed
spelling pubmed-35995882013-03-25 A neural computational model for bottom-up attention with invariant and overcomplete representation Qi, Zou Songnian, Zhao Zhe, Wang Yaping, Huang BMC Neurosci Research Article BACKGROUND: An important problem in selective attention is determining the ways the primary visual cortex contributes to the encoding of bottom-up saliency and the types of neural computation that are effective to model this process. To address this problem, we constructed a two-layered network that satisfies the neurobiological constraints of the primary visual cortex to detect salient objects. We carried out experiments on both synthetic images and natural images to explore the influences of different factors, such as network structure, the size of each layer, the type of suppression and the combination strategy, on saliency detection performance. RESULTS: The experimental results statistically demonstrated that the type and scale of filters contribute greatly to the encoding of bottom-up saliency. These two factors correspond to the mechanisms of invariant encoding and overcomplete representation in the primary visual cortex. CONCLUSIONS: (1) Instead of constructing Gabor functions or Gaussian pyramids filters for feature extraction as traditional attention models do, we learn overcomplete basis sets from natural images to extract features for saliency detection. Experiments show that given the proper layer size and a robust combination strategy, the learned overcomplete basis set outperforms a complete set and Gabor pyramids in visual saliency detection. This finding can potentially be applied in task-dependent and supervised object detection. (2) A hierarchical coding model that can represent invariant features, is designed for the pre-attentive stage of bottom-up attention. This coding model improves robustness to noises and distractions and improves the ability of detecting salient structures, such as collinear and co-circular structures, and several composite stimuli. This result indicates that invariant representation contributes to saliency detection (popping out) in bottom-up attention. The aforementioned perspectives will significantly contribute to the in-depth understanding of the information processing mechanism in the primary visual system. BioMed Central 2012-11-29 /pmc/articles/PMC3599588/ /pubmed/23190754 http://dx.doi.org/10.1186/1471-2202-13-145 Text en Copyright ©2012 Qi et al; licensee BioMed Central Ltd. http://creativecommons.org/licenses/by/2.0 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Qi, Zou
Songnian, Zhao
Zhe, Wang
Yaping, Huang
A neural computational model for bottom-up attention with invariant and overcomplete representation
title A neural computational model for bottom-up attention with invariant and overcomplete representation
title_full A neural computational model for bottom-up attention with invariant and overcomplete representation
title_fullStr A neural computational model for bottom-up attention with invariant and overcomplete representation
title_full_unstemmed A neural computational model for bottom-up attention with invariant and overcomplete representation
title_short A neural computational model for bottom-up attention with invariant and overcomplete representation
title_sort neural computational model for bottom-up attention with invariant and overcomplete representation
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3599588/
https://www.ncbi.nlm.nih.gov/pubmed/23190754
http://dx.doi.org/10.1186/1471-2202-13-145
work_keys_str_mv AT qizou aneuralcomputationalmodelforbottomupattentionwithinvariantandovercompleterepresentation
AT songnianzhao aneuralcomputationalmodelforbottomupattentionwithinvariantandovercompleterepresentation
AT zhewang aneuralcomputationalmodelforbottomupattentionwithinvariantandovercompleterepresentation
AT yapinghuang aneuralcomputationalmodelforbottomupattentionwithinvariantandovercompleterepresentation
AT qizou neuralcomputationalmodelforbottomupattentionwithinvariantandovercompleterepresentation
AT songnianzhao neuralcomputationalmodelforbottomupattentionwithinvariantandovercompleterepresentation
AT zhewang neuralcomputationalmodelforbottomupattentionwithinvariantandovercompleterepresentation
AT yapinghuang neuralcomputationalmodelforbottomupattentionwithinvariantandovercompleterepresentation