Cargando…
A novel fully convolutional network for visual saliency prediction
A human Visual System (HVS) has the ability to pay visual attention, which is one of the many functions of the HVS. Despite the many advancements being made in visual saliency prediction, there continues to be room for improvement. Deep learning has recently been used to deal with this task. This st...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
PeerJ Inc.
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7924520/ https://www.ncbi.nlm.nih.gov/pubmed/33816931 http://dx.doi.org/10.7717/peerj-cs.280 |
_version_ | 1783659107120578560 |
---|---|
author | Ghariba, Bashir Muftah Shehata, Mohamed S. McGuire, Peter |
author_facet | Ghariba, Bashir Muftah Shehata, Mohamed S. McGuire, Peter |
author_sort | Ghariba, Bashir Muftah |
collection | PubMed |
description | A human Visual System (HVS) has the ability to pay visual attention, which is one of the many functions of the HVS. Despite the many advancements being made in visual saliency prediction, there continues to be room for improvement. Deep learning has recently been used to deal with this task. This study proposes a novel deep learning model based on a Fully Convolutional Network (FCN) architecture. The proposed model is trained in an end-to-end style and designed to predict visual saliency. The entire proposed model is fully training style from scratch to extract distinguishing features. The proposed model is evaluated using several benchmark datasets, such as MIT300, MIT1003, TORONTO, and DUT-OMRON. The quantitative and qualitative experiment analyses demonstrate that the proposed model achieves superior performance for predicting visual saliency. |
format | Online Article Text |
id | pubmed-7924520 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | PeerJ Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-79245202021-04-02 A novel fully convolutional network for visual saliency prediction Ghariba, Bashir Muftah Shehata, Mohamed S. McGuire, Peter PeerJ Comput Sci Computer Vision A human Visual System (HVS) has the ability to pay visual attention, which is one of the many functions of the HVS. Despite the many advancements being made in visual saliency prediction, there continues to be room for improvement. Deep learning has recently been used to deal with this task. This study proposes a novel deep learning model based on a Fully Convolutional Network (FCN) architecture. The proposed model is trained in an end-to-end style and designed to predict visual saliency. The entire proposed model is fully training style from scratch to extract distinguishing features. The proposed model is evaluated using several benchmark datasets, such as MIT300, MIT1003, TORONTO, and DUT-OMRON. The quantitative and qualitative experiment analyses demonstrate that the proposed model achieves superior performance for predicting visual saliency. PeerJ Inc. 2020-07-13 /pmc/articles/PMC7924520/ /pubmed/33816931 http://dx.doi.org/10.7717/peerj-cs.280 Text en ©2020 Ghariba et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited. |
spellingShingle | Computer Vision Ghariba, Bashir Muftah Shehata, Mohamed S. McGuire, Peter A novel fully convolutional network for visual saliency prediction |
title | A novel fully convolutional network for visual saliency prediction |
title_full | A novel fully convolutional network for visual saliency prediction |
title_fullStr | A novel fully convolutional network for visual saliency prediction |
title_full_unstemmed | A novel fully convolutional network for visual saliency prediction |
title_short | A novel fully convolutional network for visual saliency prediction |
title_sort | novel fully convolutional network for visual saliency prediction |
topic | Computer Vision |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7924520/ https://www.ncbi.nlm.nih.gov/pubmed/33816931 http://dx.doi.org/10.7717/peerj-cs.280 |
work_keys_str_mv | AT gharibabashirmuftah anovelfullyconvolutionalnetworkforvisualsaliencyprediction AT shehatamohameds anovelfullyconvolutionalnetworkforvisualsaliencyprediction AT mcguirepeter anovelfullyconvolutionalnetworkforvisualsaliencyprediction AT gharibabashirmuftah novelfullyconvolutionalnetworkforvisualsaliencyprediction AT shehatamohameds novelfullyconvolutionalnetworkforvisualsaliencyprediction AT mcguirepeter novelfullyconvolutionalnetworkforvisualsaliencyprediction |