Towards an active foveated approach to computer vision

Autores
Dematties, Dario Jesus; Rizzi, Silvio; Thiruvathukal, George; Wainselboim, Alejandro Javier
Año de publicación
2022
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
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 enhances 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.
Fil: Dematties, Dario Jesus. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza. Instituto de Ciencias Humanas, Sociales y Ambientales; Argentina. Northwestern University; Estados Unidos
Fil: Rizzi, Silvio. Argonne National Laboratory; Estados Unidos
Fil: Thiruvathukal, George. Loyola University; Estados Unidos
Fil: Wainselboim, Alejandro Javier. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza. Instituto de Ciencias Humanas, Sociales y Ambientales; Argentina
Materia
FOVEATED COMPUTER VISION
GENERAL-PURPOSE GRAPHICS PROCESSING UNITS (GPGPUS)
REINFORCEMENT LEARNING
SACCADIC BEHAVIOR
SELF-SUPERVISED LEARNING
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/203696
Acceder
id CONICETDig_2cb26c521e6852f47f2cd84043f8a9f8
oai_identifier_str oai:ri.conicet.gov.ar:11336/203696
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Towards an active foveated approach to computer visionDematties, Dario JesusRizzi, SilvioThiruvathukal, GeorgeWainselboim, Alejandro JavierFOVEATED COMPUTER VISIONGENERAL-PURPOSE GRAPHICS PROCESSING UNITS (GPGPUS)REINFORCEMENT LEARNINGSACCADIC BEHAVIORSELF-SUPERVISED LEARNINGhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1In 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 enhances 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.Fil: Dematties, Dario Jesus. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza. Instituto de Ciencias Humanas, Sociales y Ambientales; Argentina. Northwestern University; Estados UnidosFil: Rizzi, Silvio. Argonne National Laboratory; Estados UnidosFil: Thiruvathukal, George. Loyola University; Estados UnidosFil: Wainselboim, Alejandro Javier. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza. Instituto de Ciencias Humanas, Sociales y Ambientales; ArgentinaInstituto Politecnico Nacional2022-08info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/203696Dematties, Dario Jesus; Rizzi, Silvio; Thiruvathukal, George; Wainselboim, Alejandro Javier; Towards an active foveated approach to computer vision; Instituto Politecnico Nacional; Computación y Sistemas; 26; 4; 8-2022; 1635-16472007-97371405-5546CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://cys.cic.ipn.mx/ojs/index.php/CyS/article/view/4436info:eu-repo/semantics/altIdentifier/url/https://www.scielo.org.mx/scielo.php?pid=S1405-55462022000401635&script=sci_arttextinfo:eu-repo/semantics/altIdentifier/doi/10.13053/cys-26-4-4436info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-03T09:57:33Zoai:ri.conicet.gov.ar:11336/203696instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-03 09:57:33.325CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Towards an active foveated approach to computer vision
title Towards an active foveated approach to computer vision
spellingShingle Towards an active foveated approach to computer vision
Dematties, Dario Jesus
FOVEATED COMPUTER VISION
GENERAL-PURPOSE GRAPHICS PROCESSING UNITS (GPGPUS)
REINFORCEMENT LEARNING
SACCADIC BEHAVIOR
SELF-SUPERVISED LEARNING
title_short Towards an active foveated approach to computer vision
title_full Towards an active foveated approach to computer vision
title_fullStr Towards an active foveated approach to computer vision
title_full_unstemmed Towards an active foveated approach to computer vision
title_sort Towards an active foveated approach to computer vision
dc.creator.none.fl_str_mv Dematties, Dario Jesus
Rizzi, Silvio
Thiruvathukal, George
Wainselboim, Alejandro Javier
author Dematties, Dario Jesus
author_facet Dematties, Dario Jesus
Rizzi, Silvio
Thiruvathukal, George
Wainselboim, Alejandro Javier
author_role author
author2 Rizzi, Silvio
Thiruvathukal, George
Wainselboim, Alejandro Javier
author2_role author
author
author
dc.subject.none.fl_str_mv FOVEATED COMPUTER VISION
GENERAL-PURPOSE GRAPHICS PROCESSING UNITS (GPGPUS)
REINFORCEMENT LEARNING
SACCADIC BEHAVIOR
SELF-SUPERVISED LEARNING
topic FOVEATED COMPUTER VISION
GENERAL-PURPOSE GRAPHICS PROCESSING UNITS (GPGPUS)
REINFORCEMENT LEARNING
SACCADIC BEHAVIOR
SELF-SUPERVISED LEARNING
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv 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 enhances 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.
Fil: Dematties, Dario Jesus. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza. Instituto de Ciencias Humanas, Sociales y Ambientales; Argentina. Northwestern University; Estados Unidos
Fil: Rizzi, Silvio. Argonne National Laboratory; Estados Unidos
Fil: Thiruvathukal, George. Loyola University; Estados Unidos
Fil: Wainselboim, Alejandro Javier. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza. Instituto de Ciencias Humanas, Sociales y Ambientales; Argentina
description 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 enhances 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.
publishDate 2022
dc.date.none.fl_str_mv 2022-08
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/203696
Dematties, Dario Jesus; Rizzi, Silvio; Thiruvathukal, George; Wainselboim, Alejandro Javier; Towards an active foveated approach to computer vision; Instituto Politecnico Nacional; Computación y Sistemas; 26; 4; 8-2022; 1635-1647
2007-9737
1405-5546
CONICET Digital
CONICET
url http://hdl.handle.net/11336/203696
identifier_str_mv Dematties, Dario Jesus; Rizzi, Silvio; Thiruvathukal, George; Wainselboim, Alejandro Javier; Towards an active foveated approach to computer vision; Instituto Politecnico Nacional; Computación y Sistemas; 26; 4; 8-2022; 1635-1647
2007-9737
1405-5546
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://cys.cic.ipn.mx/ojs/index.php/CyS/article/view/4436
info:eu-repo/semantics/altIdentifier/url/https://www.scielo.org.mx/scielo.php?pid=S1405-55462022000401635&script=sci_arttext
info:eu-repo/semantics/altIdentifier/doi/10.13053/cys-26-4-4436
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Instituto Politecnico Nacional
publisher.none.fl_str_mv Instituto Politecnico Nacional
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1842269468128968704
score 13.13397

Publicaciones similares