Emergence of foveal image sampling from learning to attend in visual scenes

11/28/2016
by   Brian Cheung, et al.
0

We describe a neural attention model with a learnable retinal sampling lattice. The model is trained on a visual search task requiring the classification of an object embedded in a visual scene amidst background distractors using the smallest number of fixations. We explore the tiling properties that emerge in the model's retinal sampling lattice after training. Specifically, we show that this lattice resembles the eccentricity dependent sampling lattice of the primate retina, with a high resolution region in the fovea surrounded by a low resolution periphery. Furthermore, we find conditions where these emergent properties are amplified or eliminated providing clues to their function.

READ FULL TEXT

page 5

page 6

page 7

research
07/02/2018

Neural Lattice Decoders

Lattice decoders constructed with neural networks are presented. Firstly...
research
07/24/2019

A General Theory of Concept Lattice (I): Emergence of General Concept Lattice

As the first part of the treatise on A General Theory of Concept Lattice...
research
06/12/2018

A Connectome Based Hexagonal Lattice Convolutional Network Model of the Drosophila Visual System

What can we learn from a connectome? We constructed a simplified model o...
research
02/20/2022

Statistical and Topological Summaries Aid Disease Detection for Segmented Retinal Vascular Images

Disease complications can alter vascular network morphology and disrupt ...
research
11/15/2013

Mixing Energy Models in Genetic Algorithms for On-Lattice Protein Structure Prediction

Protein structure prediction (PSP) is computationally a very challenging...
research
01/24/2017

Learning an attention model in an artificial visual system

The Human visual perception of the world is of a large fixed image that ...
research
06/24/2020

Lattice Representation Learning

In this article we introduce theory and algorithms for learning discrete...

Please sign up or login with your details

Forgot password? Click here to reset