Generalizing max pooling via (a, b)-grouping functions for convolutional neural networks

Versión resumida en castellano: https://academica-e.unavarra.es/handle/2454/53324

Detalles Bibliográficos
Autores: Rodríguez Martínez, Iosu, Da Cruz Asmus, Tiago, Pereira Dimuro, Graçaliz, Herrera, Francisco, Takáč, Zdenko, Bustince Sola, Humberto
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2023
País:España
Institución:Universidad Pública de Navarra
Repositorio:Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
OAI Identifier:oai:academica-e.unavarra.es:2454/46368
Acceso en línea:https://hdl.handle.net/2454/46368
Access Level:acceso abierto
Palabra clave:Convolutional neural networks
Grouping functions
Pooling functions
Image classification
id ES_eb5bc78f57cdaa30b2d57ea61d3747b2
oai_identifier_str oai:academica-e.unavarra.es:2454/46368
network_acronym_str ES
network_name_str España
repository_id_str
spelling Generalizing max pooling via (a, b)-grouping functions for convolutional neural networksRodríguez Martínez, IosuDa Cruz Asmus, TiagoPereira Dimuro, GraçalizHerrera, FranciscoTakáč, ZdenkoBustince Sola, HumbertoConvolutional neural networksGrouping functionsPooling functionsImage classificationVersión resumida en castellano: https://academica-e.unavarra.es/handle/2454/53324Due to their high adaptability to varied settings and effective optimization algorithm, Convolutional Neural Networks (CNNs) have set the state-of-the-art on image processing jobs for the previous decade. CNNs work in a sequential fashion, alternating between extracting significant features from an input image and aggregating these features locally through ‘‘pooling" functions, in order to produce a more compact representation. Functions like the arithmetic mean or, more typically, the maximum are commonly used to perform this downsampling operation. Despite the fact that many studies have been devoted to the development of alternative pooling algorithms, in practice, ‘‘max-pooling" still equals or exceeds most of these possibilities, and has become the standard for CNN construction. In this paper we focus on the properties that make the maximum such an efficient solution in the context of CNN feature downsampling and propose its replacement by grouping functions, a family of functions that share those desirable properties. In order to adapt these functions to the context of CNNs, we present (, )- grouping functions, an extension of grouping functions to work with real valued data. We present different construction methods for (, )-grouping functions, and demonstrate their empirical applicability for replacing max-pooling by using them to replace the pooling function of many well-known CNN architectures, finding promising results.The authors gratefully acknowledge the financial support of Tracasa Instrumental (iTRACASA) and of the Gobierno de Navarra - Departamento de Universidad, Innovación y Transformación Digital, as well as that of the Spanish Ministry of Science (project PID2019-108392GB-I00 (AEI/10.13039/501100011033)) and the project PC095-096 FUSIPROD. T. Asmus and G.P. Dimuro are supported by the projects CNPq (301618/2019-4) and FAPERGS (19/2551-0001279-9). F. Herrera is supported by the Andalusian Excellence project P18-FR4961. Z. Takáč is supported by grant VEGA 1/0267/21. Open access funding provided by Universidad Pública de Navarra.ElsevierEstadística, Informática y MatemáticasEstatistika, Informatika eta MatematikaInstitute of Smart Cities - ISCUniversidad Pública de Navarra / Nafarroako Unibertsitate Publikoa2023info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://hdl.handle.net/2454/46368reponame:Academica-e. Repositorio Institucional de la Universidad Pública de Navarrainstname:Universidad Pública de NavarraInglésinfo:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-108392GB-I00info:eu-repo/grantAgreement/Gobierno de Navarra//© 2023 The Author(s). This is an open access article under the CC BY license.https://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:academica-e.unavarra.es:2454/463682026-06-17T12:41:47Z
dc.title.none.fl_str_mv Generalizing max pooling via (a, b)-grouping functions for convolutional neural networks
title Generalizing max pooling via (a, b)-grouping functions for convolutional neural networks
spellingShingle Generalizing max pooling via (a, b)-grouping functions for convolutional neural networks
Rodríguez Martínez, Iosu
Convolutional neural networks
Grouping functions
Pooling functions
Image classification
title_short Generalizing max pooling via (a, b)-grouping functions for convolutional neural networks
title_full Generalizing max pooling via (a, b)-grouping functions for convolutional neural networks
title_fullStr Generalizing max pooling via (a, b)-grouping functions for convolutional neural networks
title_full_unstemmed Generalizing max pooling via (a, b)-grouping functions for convolutional neural networks
title_sort Generalizing max pooling via (a, b)-grouping functions for convolutional neural networks
dc.creator.none.fl_str_mv Rodríguez Martínez, Iosu
Da Cruz Asmus, Tiago
Pereira Dimuro, Graçaliz
Herrera, Francisco
Takáč, Zdenko
Bustince Sola, Humberto
author Rodríguez Martínez, Iosu
author_facet Rodríguez Martínez, Iosu
Da Cruz Asmus, Tiago
Pereira Dimuro, Graçaliz
Herrera, Francisco
Takáč, Zdenko
Bustince Sola, Humberto
author_role author
author2 Da Cruz Asmus, Tiago
Pereira Dimuro, Graçaliz
Herrera, Francisco
Takáč, Zdenko
Bustince Sola, Humberto
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Estadística, Informática y Matemáticas
Estatistika, Informatika eta Matematika
Institute of Smart Cities - ISC
Universidad Pública de Navarra / Nafarroako Unibertsitate Publikoa
dc.subject.none.fl_str_mv Convolutional neural networks
Grouping functions
Pooling functions
Image classification
topic Convolutional neural networks
Grouping functions
Pooling functions
Image classification
description Versión resumida en castellano: https://academica-e.unavarra.es/handle/2454/53324
publishDate 2023
dc.date.none.fl_str_mv 2023
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/2454/46368
url https://hdl.handle.net/2454/46368
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-108392GB-I00
info:eu-repo/grantAgreement/Gobierno de Navarra//
dc.rights.none.fl_str_mv © 2023 The Author(s). This is an open access article under the CC BY license.
https://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv © 2023 The Author(s). This is an open access article under the CC BY license.
https://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
instname:Universidad Pública de Navarra
instname_str Universidad Pública de Navarra
reponame_str Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
collection Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869423220692615168
score 15,300724

Similares en LA Referencia