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

Ozimek, Piotr and Hristozova, Nina and Balog, Lorinc and Siebert, Jan Paul (2019) A Space-Variant Visual Pathway Model for Data Efficient Deep Learning. Frontiers in Cellular Neuroscience, 13. ISSN 1662-5102

[thumbnail of pubmed-zip/versions/1/package-entries/fncel-13-00036/fncel-13-00036.pdf] Text
pubmed-zip/versions/1/package-entries/fncel-13-00036/fncel-13-00036.pdf - Published Version
Download (4MB)

Abstract

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: Article
Subjects: Librbary Digital > Medical Science
Depositing User: Unnamed user with email support@librbarydigit.com
Date Deposited: 27 May 2023 06:22
Last Modified: 20 Aug 2025 05:11
URI: http://index.go2articles.com/id/eprint/783

Actions (login required)

View Item
View Item