AUTHOR=Ozimek Piotr , Hristozova Nina , Balog Lorinc , Siebert Jan Paul 

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

JOURNAL=Frontiers in Cellular Neuroscience

VOLUME=Volume 13 - 2019

YEAR=2019

URL=https://www.frontiersin.org/journals/cellular-neuroscience/articles/10.3389/fncel.2019.00036

DOI=10.3389/fncel.2019.00036

ISSN=1662-5102

ABSTRACT=<p>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 <italic>one million pixels</italic> in size, <italic>in real time</italic>, using only consumer grade graphics processor (GPU) hardware <italic>in a single pass of the DCNN</italic>.</p>