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

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...

Full description

Bibliographic Details
Main Authors: Piotr Ozimek, Nina Hristozova, Lorinc Balog, Jan Paul Siebert
Format: Article
Language:English
Published: Frontiers Media S.A. 2019-03-01
Series:Frontiers in Cellular Neuroscience
Subjects:
data efficiency
deep learning
retina
foveated vision
biological vision
egocentric perception
Online Access:https://www.frontiersin.org/article/10.3389/fncel.2019.00036/full
id doaj-4488c78b2e1b4bfda7f62cedf6aafd10
record_format Article
spelling doaj-4488c78b2e1b4bfda7f62cedf6aafd102020-11-25T01:00:23ZengFrontiers Media S.A.Frontiers in Cellular Neuroscience1662-51022019-03-011310.3389/fncel.2019.00036427977A Space-Variant Visual Pathway Model for Data Efficient Deep LearningPiotr OzimekNina HristozovaLorinc BalogJan Paul SiebertWe 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.https://www.frontiersin.org/article/10.3389/fncel.2019.00036/fulldata efficiencydeep learningretinafoveated visionbiological visionegocentric perception
collection DOAJ
language English
format Article
sources DOAJ
author Piotr Ozimek
Nina Hristozova
Lorinc Balog
Jan Paul Siebert
spellingShingle Piotr Ozimek
Nina Hristozova
Lorinc Balog
Jan Paul Siebert
A Space-Variant Visual Pathway Model for Data Efficient Deep Learning
Frontiers in Cellular Neuroscience
data efficiency
deep learning
retina
foveated vision
biological vision
egocentric perception
author_facet Piotr Ozimek
Nina Hristozova
Lorinc Balog
Jan Paul Siebert
author_sort Piotr Ozimek
title 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_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_sort space-variant visual pathway model for data efficient deep learning
publisher Frontiers Media S.A.
series Frontiers in Cellular Neuroscience
issn 1662-5102
publishDate 2019-03-01
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.
topic data efficiency
deep learning
retina
foveated vision
biological vision
egocentric perception
url https://www.frontiersin.org/article/10.3389/fncel.2019.00036/full
work_keys_str_mv AT piotrozimek aspacevariantvisualpathwaymodelfordataefficientdeeplearning
AT ninahristozova aspacevariantvisualpathwaymodelfordataefficientdeeplearning
AT lorincbalog aspacevariantvisualpathwaymodelfordataefficientdeeplearning
AT janpaulsiebert aspacevariantvisualpathwaymodelfordataefficientdeeplearning
AT piotrozimek spacevariantvisualpathwaymodelfordataefficientdeeplearning
AT ninahristozova spacevariantvisualpathwaymodelfordataefficientdeeplearning
AT lorincbalog spacevariantvisualpathwaymodelfordataefficientdeeplearning
AT janpaulsiebert spacevariantvisualpathwaymodelfordataefficientdeeplearning
_version_ 1725213762713026560

Similar Items