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
Description
Summary: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.
ISSN:1662-5102

Similar Items