On the relevance of the metadata used in the semantic segmentation of indoor image spaces

Descripción del Articulo

This work has been partially funded by the Spanish Ministry of Sci-ence, Education and Universities, the European Regional DevelopmentFund and the State Research Agency [grant number RTI2018-098156-B-C52], and by FONDECYT / World Bank [grant number 026-2019FONDECYT-BM-INC.INV].
Detalles Bibliográficos
Autores: Vasquez-Espinoza L., Castillo-Cara M., Orozco-Barbosa L.
Formato: artículo
Fecha de Publicación:2021
Institución:Consejo Nacional de Ciencia Tecnología e Innovación
Repositorio:CONCYTEC-Institucional
Lenguaje:inglés
OAI Identifier:oai:repositorio.concytec.gob.pe:20.500.12390/3030
Enlace del recurso:https://hdl.handle.net/20.500.12390/3030
https://doi.org/10.1016/j.eswa.2021.115486
Nivel de acceso:acceso abierto
Materia:U-net
Deep learning
Fully convolutional network
Indoor scenes
Metadata preprocessing
Semantic segmentation
https://purl.org/pe-repo/ocde/ford#2.02.04
id CONC_0e93590debcf6098e337091fcca2247e
oai_identifier_str oai:repositorio.concytec.gob.pe:20.500.12390/3030
network_acronym_str CONC
network_name_str CONCYTEC-Institucional
repository_id_str 4689
dc.title.none.fl_str_mv On the relevance of the metadata used in the semantic segmentation of indoor image spaces
title On the relevance of the metadata used in the semantic segmentation of indoor image spaces
spellingShingle On the relevance of the metadata used in the semantic segmentation of indoor image spaces
Vasquez-Espinoza L.
U-net
Deep learning
Deep learning
Fully convolutional network
Fully convolutional network
Indoor scenes
Indoor scenes
Metadata preprocessing
Metadata preprocessing
Semantic segmentation
Semantic segmentation
https://purl.org/pe-repo/ocde/ford#2.02.04
title_short On the relevance of the metadata used in the semantic segmentation of indoor image spaces
title_full On the relevance of the metadata used in the semantic segmentation of indoor image spaces
title_fullStr On the relevance of the metadata used in the semantic segmentation of indoor image spaces
title_full_unstemmed On the relevance of the metadata used in the semantic segmentation of indoor image spaces
title_sort On the relevance of the metadata used in the semantic segmentation of indoor image spaces
author Vasquez-Espinoza L.
author_facet Vasquez-Espinoza L.
Castillo-Cara M.
Orozco-Barbosa L.
author_role author
author2 Castillo-Cara M.
Orozco-Barbosa L.
author2_role author
author
dc.contributor.author.fl_str_mv Vasquez-Espinoza L.
Castillo-Cara M.
Orozco-Barbosa L.
dc.subject.none.fl_str_mv U-net
topic U-net
Deep learning
Deep learning
Fully convolutional network
Fully convolutional network
Indoor scenes
Indoor scenes
Metadata preprocessing
Metadata preprocessing
Semantic segmentation
Semantic segmentation
https://purl.org/pe-repo/ocde/ford#2.02.04
dc.subject.es_PE.fl_str_mv Deep learning
Deep learning
Fully convolutional network
Fully convolutional network
Indoor scenes
Indoor scenes
Metadata preprocessing
Metadata preprocessing
Semantic segmentation
Semantic segmentation
dc.subject.ocde.none.fl_str_mv https://purl.org/pe-repo/ocde/ford#2.02.04
description This work has been partially funded by the Spanish Ministry of Sci-ence, Education and Universities, the European Regional DevelopmentFund and the State Research Agency [grant number RTI2018-098156-B-C52], and by FONDECYT / World Bank [grant number 026-2019FONDECYT-BM-INC.INV].
publishDate 2021
dc.date.accessioned.none.fl_str_mv 2024-05-30T23:13:38Z
dc.date.available.none.fl_str_mv 2024-05-30T23:13:38Z
dc.date.issued.fl_str_mv 2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.uri.none.fl_str_mv https://hdl.handle.net/20.500.12390/3030
dc.identifier.doi.none.fl_str_mv https://doi.org/10.1016/j.eswa.2021.115486
dc.identifier.scopus.none.fl_str_mv 2-s2.0-85109921392
url https://hdl.handle.net/20.500.12390/3030
https://doi.org/10.1016/j.eswa.2021.115486
identifier_str_mv 2-s2.0-85109921392
dc.language.iso.none.fl_str_mv eng
language eng
dc.relation.ispartof.none.fl_str_mv Expert Systems with Applications
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
dc.rights.uri.none.fl_str_mv https://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.publisher.none.fl_str_mv Elsevier Ltd
publisher.none.fl_str_mv Elsevier Ltd
dc.source.none.fl_str_mv reponame:CONCYTEC-Institucional
instname:Consejo Nacional de Ciencia Tecnología e Innovación
instacron:CONCYTEC
instname_str Consejo Nacional de Ciencia Tecnología e Innovación
instacron_str CONCYTEC
institution CONCYTEC
reponame_str CONCYTEC-Institucional
collection CONCYTEC-Institucional
repository.name.fl_str_mv Repositorio Institucional CONCYTEC
repository.mail.fl_str_mv repositorio@concytec.gob.pe
_version_ 1844331697810702336
spelling Publicationrp08674600rp01248600rp01251600Vasquez-Espinoza L.Castillo-Cara M.Orozco-Barbosa L.2024-05-30T23:13:38Z2024-05-30T23:13:38Z2021https://hdl.handle.net/20.500.12390/3030https://doi.org/10.1016/j.eswa.2021.1154862-s2.0-85109921392This work has been partially funded by the Spanish Ministry of Sci-ence, Education and Universities, the European Regional DevelopmentFund and the State Research Agency [grant number RTI2018-098156-B-C52], and by FONDECYT / World Bank [grant number 026-2019FONDECYT-BM-INC.INV].The study of artificial learning processes in the area of computer vision context has mainly focused on achieving a fixed output target rather than on identifying the underlying processes as a means to develop solutions capable of performing as good as or better than the human brain. This work reviews the well-known segmentation efforts in computer vision. However, our primary focus is on the quantitative evaluation of the amount of contextual information provided to the neural network. In particular, the information used to mimic the tacit information that a human is capable of using, like a sense of unambiguous order and the capability of improving its estimation by complementing already learned information. Our results show that, after a set of pre and post-processing methods applied to both the training data and the neural network architecture, the predictions made were drastically closer to the expected output in comparison to the cases where no contextual additions were provided. Our results provide evidence that learning systems strongly rely on contextual information for the identification task process. © 2021 The Author(s)Consejo Nacional de Ciencia, Tecnología e Innovación Tecnológica - ConcytecengElsevier LtdExpert Systems with Applicationsinfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-nd/4.0/U-netDeep learning-1Deep learning-1Fully convolutional network-1Fully convolutional network-1Indoor scenes-1Indoor scenes-1Metadata preprocessing-1Metadata preprocessing-1Semantic segmentation-1Semantic segmentation-1https://purl.org/pe-repo/ocde/ford#2.02.04-1On the relevance of the metadata used in the semantic segmentation of indoor image spacesinfo:eu-repo/semantics/articlereponame:CONCYTEC-Institucionalinstname:Consejo Nacional de Ciencia Tecnología e Innovacióninstacron:CONCYTEC20.500.12390/3030oai:repositorio.concytec.gob.pe:20.500.12390/30302024-05-30 16:13:17.954https://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_14cbinfo:eu-repo/semantics/closedAccessmetadata only accesshttps://repositorio.concytec.gob.peRepositorio Institucional CONCYTECrepositorio@concytec.gob.pe#PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE#<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="2f061a5b-8c31-47b3-b95e-f849c21cf37d"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>On the relevance of the metadata used in the semantic segmentation of indoor image spaces</Title> <PublishedIn> <Publication> <Title>Expert Systems with Applications</Title> </Publication> </PublishedIn> <PublicationDate>2021</PublicationDate> <DOI>https://doi.org/10.1016/j.eswa.2021.115486</DOI> <SCP-Number>2-s2.0-85109921392</SCP-Number> <Authors> <Author> <DisplayName>Vasquez-Espinoza L.</DisplayName> <Person id="rp08674" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Castillo-Cara M.</DisplayName> <Person id="rp01248" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> <Author> <DisplayName>Orozco-Barbosa L.</DisplayName> <Person id="rp01251" /> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Elsevier Ltd</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>https://creativecommons.org/licenses/by-nc-nd/4.0/</License> <Keyword>U-net</Keyword> <Keyword>Deep learning</Keyword> <Keyword>Deep learning</Keyword> <Keyword>Fully convolutional network</Keyword> <Keyword>Fully convolutional network</Keyword> <Keyword>Indoor scenes</Keyword> <Keyword>Indoor scenes</Keyword> <Keyword>Metadata preprocessing</Keyword> <Keyword>Metadata preprocessing</Keyword> <Keyword>Semantic segmentation</Keyword> <Keyword>Semantic segmentation</Keyword> <Abstract>The study of artificial learning processes in the area of computer vision context has mainly focused on achieving a fixed output target rather than on identifying the underlying processes as a means to develop solutions capable of performing as good as or better than the human brain. This work reviews the well-known segmentation efforts in computer vision. However, our primary focus is on the quantitative evaluation of the amount of contextual information provided to the neural network. In particular, the information used to mimic the tacit information that a human is capable of using, like a sense of unambiguous order and the capability of improving its estimation by complementing already learned information. Our results show that, after a set of pre and post-processing methods applied to both the training data and the neural network architecture, the predictions made were drastically closer to the expected output in comparison to the cases where no contextual additions were provided. Our results provide evidence that learning systems strongly rely on contextual information for the identification task process. © 2021 The Author(s)</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication> -1
score 12.811033
On the relevance of the metadata used in the semantic segmentation of indoor image spaces
Nota importante:
La información contenida en este registro es de entera responsabilidad de la institución que gestiona el repositorio institucional donde esta contenido este documento o set de datos. El CONCYTEC no se hace responsable por los contenidos (publicaciones y/o datos) accesibles a través del Repositorio Nacional Digital de Ciencia, Tecnología e Innovación de Acceso Abierto (ALICIA).

Ejemplares Similares