Deep mixed precision for hyperspectral image classification

Hyperspectral images (HSIs) record scenes at different wavelength channels, providing detailed spatial and spectral information. How to storage and process this highdimensional data plays a vital role in many practical applications, where classification technologies have emerged as excellent process...

Descripción completa

Detalles Bibliográficos
Autores: Paoletti, Mercedes Eugenia, X. Tao, Haut, Juan Mario, Moreno Álvarez, Sergio, Plaza, Antonio
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Universidad Nacional de Educación a Distancia
Repositorio:e-spacio. Repositorio Institucional de la UNED
Idioma:inglés
OAI Identifier:oai:e-spacio.uned.es:20.500.14468/24389
Acceso en línea:https://hdl.handle.net/20.500.14468/24389
Access Level:acceso abierto
Palabra clave:12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informática
hyperspectral image
deeplearning
mixed precision
id ES_2bf780420ecb4dd8566b5e484aa28fee
oai_identifier_str oai:e-spacio.uned.es:20.500.14468/24389
network_acronym_str ES
network_name_str España
repository_id_str
spelling Deep mixed precision for hyperspectral image classificationPaoletti, Mercedes EugeniaX. TaoHaut, Juan MarioMoreno Álvarez, SergioPlaza, Antonio12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informáticahyperspectral imagedeeplearningmixed precisionHyperspectral images (HSIs) record scenes at different wavelength channels, providing detailed spatial and spectral information. How to storage and process this highdimensional data plays a vital role in many practical applications, where classification technologies have emerged as excellent processing tools. However, their high computational complexity and energy requirements bring some challenges. Adopting low-power consumption architectures and deep learning (DL) approaches has to provide acceptable computing capabilities without reducing accuracy demand. However, most DL architectures employ single-precision (FP32) to train models, and some big DL architectures will have a limitation on memory and computation resources. This can negatively affect the network learning process. This letter leads these challenges by using mixed precision into DL architectures for HSI classification to speed up the training process and reduce the memory consumption/access. Proposed models are evaluated on four widely used data sets. Also, low and highpower consumption devices are compared, considering NVIDIA Jetson Xavier and Titan RTX GPUs, to evaluate the proposal viability in on-board processing devices. Obtained results demonstrate the efficiency and effectiveness of these models within HSI classification task for both devices. Source codes: https ://githu b.com/mhaut / CNN-MP-HSI.Springerhttps://orcid.org/0000-0003-1030-3729https://orcid.org/0000-0001-6701-961Xhttps://orcid.org/0000-0002-9613-1659e-Spacio UNED20242024-11-1520212021-02-0320212021-02-03journal articlehttp://purl.org/coar/resource_type/c_6501info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/20.500.14468/24389reponame:e-spacio. Repositorio Institucional de la UNEDinstname:Universidad Nacional de Educación a DistanciaInglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-nd/4.0/deed.esoai:e-spacio.uned.es:20.500.14468/243892026-06-06T12:38:31Z
dc.title.none.fl_str_mv Deep mixed precision for hyperspectral image classification
title Deep mixed precision for hyperspectral image classification
spellingShingle Deep mixed precision for hyperspectral image classification
Paoletti, Mercedes Eugenia
12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informática
hyperspectral image
deeplearning
mixed precision
title_short Deep mixed precision for hyperspectral image classification
title_full Deep mixed precision for hyperspectral image classification
title_fullStr Deep mixed precision for hyperspectral image classification
title_full_unstemmed Deep mixed precision for hyperspectral image classification
title_sort Deep mixed precision for hyperspectral image classification
dc.creator.none.fl_str_mv Paoletti, Mercedes Eugenia
X. Tao
Haut, Juan Mario
Moreno Álvarez, Sergio
Plaza, Antonio
author Paoletti, Mercedes Eugenia
author_facet Paoletti, Mercedes Eugenia
X. Tao
Haut, Juan Mario
Moreno Álvarez, Sergio
Plaza, Antonio
author_role author
author2 X. Tao
Haut, Juan Mario
Moreno Álvarez, Sergio
Plaza, Antonio
author2_role author
author
author
author
dc.contributor.none.fl_str_mv https://orcid.org/0000-0003-1030-3729
https://orcid.org/0000-0001-6701-961X
https://orcid.org/0000-0002-9613-1659
e-Spacio UNED
dc.subject.none.fl_str_mv 12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informática
hyperspectral image
deeplearning
mixed precision
topic 12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informática
hyperspectral image
deeplearning
mixed precision
description Hyperspectral images (HSIs) record scenes at different wavelength channels, providing detailed spatial and spectral information. How to storage and process this highdimensional data plays a vital role in many practical applications, where classification technologies have emerged as excellent processing tools. However, their high computational complexity and energy requirements bring some challenges. Adopting low-power consumption architectures and deep learning (DL) approaches has to provide acceptable computing capabilities without reducing accuracy demand. However, most DL architectures employ single-precision (FP32) to train models, and some big DL architectures will have a limitation on memory and computation resources. This can negatively affect the network learning process. This letter leads these challenges by using mixed precision into DL architectures for HSI classification to speed up the training process and reduce the memory consumption/access. Proposed models are evaluated on four widely used data sets. Also, low and highpower consumption devices are compared, considering NVIDIA Jetson Xavier and Titan RTX GPUs, to evaluate the proposal viability in on-board processing devices. Obtained results demonstrate the efficiency and effectiveness of these models within HSI classification task for both devices. Source codes: https ://githu b.com/mhaut / CNN-MP-HSI.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-02-03
2021
2021-02-03
2024
2024-11-15
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/20.500.14468/24389
url https://hdl.handle.net/20.500.14468/24389
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
http://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:e-spacio. Repositorio Institucional de la UNED
instname:Universidad Nacional de Educación a Distancia
instname_str Universidad Nacional de Educación a Distancia
reponame_str e-spacio. Repositorio Institucional de la UNED
collection e-spacio. Repositorio Institucional de la UNED
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869405196909543424
score 15,811543

Similares en LA Referencia