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

Vista sencilla de ítem
dc.contributor.authorVasquez Espinoza, Luis
dc.contributor.authorOrozco Barbosa, Luis
dc.contributor.authorCastillo Cara, José Manuel
dc.date.accessioned2024-05-20T11:34:23Z
dc.date.available2024-05-20T11:34:23Z
dc.date.issued2021
dc.description.abstractThe 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.en
dc.description.versionversión publicada
dc.identifier.doihttps://doi.org/10.1016/j.eswa.2021.115486
dc.identifier.issn0957-4174
dc.identifier.urihttps://hdl.handle.net/20.500.14468/12242
dc.journal.titleExpert Systems With Applications
dc.journal.volume184
dc.language.isoen
dc.publisherElsevier
dc.relation.centerE.T.S. de Ingeniería Informática
dc.relation.departmentInformática y Automática
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0
dc.subject.keywordsDeep learning
dc.subject.keywordsU-net
dc.subject.keywordsSemantic segmentation
dc.subject.keywordsMetadata preprocessing
dc.subject.keywordsFully convolutional network
dc.subject.keywordsIndoor scenes
dc.titleOn the relevance of the metadata used in the semantic segmentation of indoor image spaceses
dc.typejournal articleen
dc.typeartículoes
dspace.entity.typePublication
relation.isAuthorOfPublicationc0e39bd2-c0d8-4743-953d-488baf6b977e
relation.isAuthorOfPublication.latestForDiscoveryc0e39bd2-c0d8-4743-953d-488baf6b977e
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Castillo-Cara_JM_Semantic.pdf
Tamaño:
3.09 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos y papers