A Space-Variant Visual Pathway Model for Data Efficient Deep Learning

We present an investigation into adopting a model of the retino-cortical mapping, found in biological visual systems, to improve the efficiency of image analysis using Deep Convolutional Neural Nets (DCNNs) in the context of robot vision and egocentric perception systems. This work has now enabled D...

Descripción completa

Detalles Bibliográficos
Autores principales: Ozimek, Piotr, Hristozova, Nina, Balog, Lorinc, Siebert, Jan Paul
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2019
Materias:
Neuroscience
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6444208/
https://www.ncbi.nlm.nih.gov/pubmed/30971891
http://dx.doi.org/10.3389/fncel.2019.00036
_version_ 1783407986526388224
author Ozimek, Piotr
Hristozova, Nina
Balog, Lorinc
Siebert, Jan Paul
author_facet Ozimek, Piotr
Hristozova, Nina
Balog, Lorinc
Siebert, Jan Paul
author_sort Ozimek, Piotr
collection PubMed
description We present an investigation into adopting a model of the retino-cortical mapping, found in biological visual systems, to improve the efficiency of image analysis using Deep Convolutional Neural Nets (DCNNs) in the context of robot vision and egocentric perception systems. This work has now enabled DCNNs to process input images approaching one million pixels in size, in real time, using only consumer grade graphics processor (GPU) hardware in a single pass of the DCNN.
format Online
Article
Text
id pubmed-6444208
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-64442082019-04-10 A Space-Variant Visual Pathway Model for Data Efficient Deep Learning Ozimek, Piotr Hristozova, Nina Balog, Lorinc Siebert, Jan Paul Front Cell Neurosci Neuroscience We present an investigation into adopting a model of the retino-cortical mapping, found in biological visual systems, to improve the efficiency of image analysis using Deep Convolutional Neural Nets (DCNNs) in the context of robot vision and egocentric perception systems. This work has now enabled DCNNs to process input images approaching one million pixels in size, in real time, using only consumer grade graphics processor (GPU) hardware in a single pass of the DCNN. Frontiers Media S.A. 2019-03-26 /pmc/articles/PMC6444208/ /pubmed/30971891 http://dx.doi.org/10.3389/fncel.2019.00036 Text en Copyright © 2019 Ozimek, Hristozova, Balog and Siebert. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Ozimek, Piotr
Hristozova, Nina
Balog, Lorinc
Siebert, Jan Paul
A Space-Variant Visual Pathway Model for Data Efficient Deep Learning
title A Space-Variant Visual Pathway Model for Data Efficient Deep Learning
title_full A Space-Variant Visual Pathway Model for Data Efficient Deep Learning
title_fullStr A Space-Variant Visual Pathway Model for Data Efficient Deep Learning
title_full_unstemmed A Space-Variant Visual Pathway Model for Data Efficient Deep Learning
title_short A Space-Variant Visual Pathway Model for Data Efficient Deep Learning
title_sort space-variant visual pathway model for data efficient deep learning
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6444208/
https://www.ncbi.nlm.nih.gov/pubmed/30971891
http://dx.doi.org/10.3389/fncel.2019.00036
work_keys_str_mv AT ozimekpiotr aspacevariantvisualpathwaymodelfordataefficientdeeplearning
AT hristozovanina aspacevariantvisualpathwaymodelfordataefficientdeeplearning
AT baloglorinc aspacevariantvisualpathwaymodelfordataefficientdeeplearning
AT siebertjanpaul aspacevariantvisualpathwaymodelfordataefficientdeeplearning
AT ozimekpiotr spacevariantvisualpathwaymodelfordataefficientdeeplearning
AT hristozovanina spacevariantvisualpathwaymodelfordataefficientdeeplearning
AT baloglorinc spacevariantvisualpathwaymodelfordataefficientdeeplearning
AT siebertjanpaul spacevariantvisualpathwaymodelfordataefficientdeeplearning

Ejemplares similares