A space-variant visual pathway model for data efficient deep learning

Ozimek, P., Hristozova, N., Balog, L. and Siebert, J. P. (2019) A space-variant visual pathway model for data efficient deep learning. Frontiers in Cellular Neuroscience, 13, 36. (doi: 10.3389/fncel.2019.00036)

180269.pdf - Published Version
Available under License Creative Commons Attribution.



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.

Item Type:Articles
Glasgow Author(s) Enlighten ID:Ozimek, Peter and Siebert, Dr Paul and Hristozova, Nina
Authors: Ozimek, P., Hristozova, N., Balog, L., and Siebert, J. P.
College/School:College of Science and Engineering > School of Computing Science
Journal Name:Frontiers in Cellular Neuroscience
Publisher:Frontiers Media
ISSN (Online):1662-5102
Copyright Holders:Copyright © 2019 Ozimek, Hristozova, Balog and Siebert
First Published:First published in Frontiers in Cellular Neuroscience 13: 36
Publisher Policy:Reproduced under a Creative Commons License
Data DOI:10.5525/gla.researchdata.744

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
759631iSee Intelligent Vision for GraspingJan SiebertEngineering and Physical Sciences Research Council (EPSRC)EP/R005605/1COM - COMPUTING SCIENCE
738201EPSRC DTP 16/17 and 17/18Mary Beth KneafseyEngineering and Physical Sciences Research Council (EPSRC)EP/N509668/1R&I - RESEARCH STRATEGY & INNOVATION
593891Brain reading of contextual feedback and predictions - BrainReadFBPredCodeLars MuckliEuropean Research Council (ERC)ERC-2012-Stg-311751INP - CENTRE FOR COGNITIVE NEUROIMAGING