TY - JOUR
T1 - Towards an Active Foveated Approach to Computer Vision
AU - Dematties, Dario
AU - Rizzi, Silvio
AU - Thiruvathukal, George K.
AU - Wainselboim, Alejandro Javier
N1 - Dario Dematties, Silvio Rizzi, George K. Thiruvathukal, Alejandro Wainselboim, "Towards an Active Foveated Approach to Computer Vision", Computación y Sistemas, 26(4), 2022.
PY - 2022/1/1
Y1 - 2022/1/1
N2 - In this paper, a series of experimental methods are presented explaining a new approach towards active foveated Computer Vision (CV). This is a collaborative effort between researchers at CONICET Mendoza Technological Scientific Center from Argentina, Argonne National Laboratory (ANL), and Loyola University Chicago from the US. The aim is to advance new CV approaches more in line with those found in biological agents in order to bring novel solutions to the main problems faced by current CV applications. Basically this work enhance Self-supervised (SS) learning, incorporating foveated vision plus saccadic behavior in order to improve training and computational efficiency without reducing performance significantly. This paper includes a compendium of methods’ explanations, and since this is a work that is currently in progress, only preliminary results are provided. We also make our code fully available.
AB - In this paper, a series of experimental methods are presented explaining a new approach towards active foveated Computer Vision (CV). This is a collaborative effort between researchers at CONICET Mendoza Technological Scientific Center from Argentina, Argonne National Laboratory (ANL), and Loyola University Chicago from the US. The aim is to advance new CV approaches more in line with those found in biological agents in order to bring novel solutions to the main problems faced by current CV applications. Basically this work enhance Self-supervised (SS) learning, incorporating foveated vision plus saccadic behavior in order to improve training and computational efficiency without reducing performance significantly. This paper includes a compendium of methods’ explanations, and since this is a work that is currently in progress, only preliminary results are provided. We also make our code fully available.
KW - Foveated computer vision
KW - saccadic behavior
KW - reinforcement learning
KW - self-supervised learning
KW - General-Purpose Graphics Processing Units (GPGPUs)
UR - https://ecommons.luc.edu/cs_facpubs/318
U2 - 10.13053/CyS-26-4-4436
DO - 10.13053/CyS-26-4-4436
M3 - Article
VL - 26
JO - Computer Science: Faculty Publications and Other Works
JF - Computer Science: Faculty Publications and Other Works
IS - 4
ER -