Towards an Active Foveated Approach to Computer Vision

Autores/as

  • Dario Dematties Northwestern University
  • Silvio Rizzi Argonne Leadership Computer Facility
  • George K. Thiruvathukal Loyola University Chicago
  • Alejandro Wainselboim Instituto de Ciencias Humanas, Sociales y Ambientales

DOI:

https://doi.org/10.13053/cys-26-4-4436

Palabras clave:

Foveated computer vision, saccadic behavior, reinforcement learning, self-supervised learning, General-Purpose Graphics Processing Units (GPGPUs)

Resumen

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.

Biografía del autor/a

Dario Dematties, Northwestern University

Northwestern Argonne Institute of Science and Engineering

Silvio Rizzi, Argonne Leadership Computer Facility

Argonne National Laboratory

George K. Thiruvathukal, Loyola University Chicago

Computer Science Department

Alejandro Wainselboim, Instituto de Ciencias Humanas, Sociales y Ambientales

CONICET Mendoza Technological Scientific

Descargas

Publicado

2022-12-25

Número

Sección

Artículos