EffBaGAN: an efficient balancing GAN for Earth observation in data scarcity scenarios

Generative Adversarial Networks (GAN) can be used as a data augmentation technique in scenarios with limited labeled information and class imbalances, common issues in remote sensing datasets. The EfficientNet architecture has gained attention for achieving high accuracy with moderate computational...

Descripción completa

Detalles Bibliográficos
Autores: Vilela Pérez, Nicolás, Blanco Heras, Dora, Argüello Pedreira, Francisco
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Universidad de Santiago de Compostela (USC)
Repositorio:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Idioma:inglés
OAI Identifier:oai:minerva.usc.gal:10347/38377
Acceso en línea:https://hdl.handle.net/10347/38377
Access Level:acceso abierto
Palabra clave:BAGAN
Classification
Data augmentation
EfficientNet
Multispectral
Residual generator
Transformer
Vegetation
Investigación
id ES_fb75b21ffb316988dfb5f2e1995ff5cd
oai_identifier_str oai:minerva.usc.gal:10347/38377
network_acronym_str ES
network_name_str España
repository_id_str
spelling EffBaGAN: an efficient balancing GAN for Earth observation in data scarcity scenariosVilela Pérez, NicolásBlanco Heras, DoraArgüello Pedreira, FranciscoBAGANClassificationData augmentationEfficientNetMultispectralResidual generatorTransformerVegetationInvestigaciónGenerative Adversarial Networks (GAN) can be used as a data augmentation technique in scenarios with limited labeled information and class imbalances, common issues in remote sensing datasets. The EfficientNet architecture has gained attention for achieving high accuracy with moderate computational cost. This work introduces EffBaGAN, a generative network specifically designed for the classification of multispectral remote sensing images based on EfficientNet, addressing data scarcity and class imbalances while minimizing network complexity. EffBaGAN is built upon a BAGAN architecture, incorporating a custom EfficientNet-based discriminator and generator. In particular, for the discriminator we propose RedEffDis, a reduced version of EfficientNet-B0 adapted to multispectral imagery. The generator, ResEffGen, includes a residual EfficientNet-based path, which enhances the quality of the generated synthetic samples. Additionally, a superpixel-based sample extraction procedure is used to further reduce the computational cost of the method. Experiments were conducted on large, very high-resolution multispectral images of vegetation, demonstrating that EffBaGAN achieves higher accuracy than other advanced classification methods, including vision transformers and residual BAGAN, while maintaining a significantly lower computational cost. In fact, EffBaGAN is more than twice as fast as the residual BAGAN, making it an efficient solution for remote sensing image classification in data-scarce environments.IEEEUniversidade de Santiago de Compostela. Centro de Investigación en Tecnoloxías Intelixentes da USC (CiTIUS)Universidade de Santiago de Compostela. Departamento de Electrónica e Computación20242024-12-0420242024-12-04journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/10347/38377reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostelainstname:Universidad de Santiago de Compostela (USC)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Not available Not availableAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Not available Not availableopen accesshttp://purl.org/coar/access_right/c_abf2© 2024 The Authors. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 Licensehttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:minerva.usc.gal:10347/383772026-06-15T12:47:27Z
dc.title.none.fl_str_mv EffBaGAN: an efficient balancing GAN for Earth observation in data scarcity scenarios
title EffBaGAN: an efficient balancing GAN for Earth observation in data scarcity scenarios
spellingShingle EffBaGAN: an efficient balancing GAN for Earth observation in data scarcity scenarios
Vilela Pérez, Nicolás
BAGAN
Classification
Data augmentation
EfficientNet
Multispectral
Residual generator
Transformer
Vegetation
Investigación
title_short EffBaGAN: an efficient balancing GAN for Earth observation in data scarcity scenarios
title_full EffBaGAN: an efficient balancing GAN for Earth observation in data scarcity scenarios
title_fullStr EffBaGAN: an efficient balancing GAN for Earth observation in data scarcity scenarios
title_full_unstemmed EffBaGAN: an efficient balancing GAN for Earth observation in data scarcity scenarios
title_sort EffBaGAN: an efficient balancing GAN for Earth observation in data scarcity scenarios
dc.creator.none.fl_str_mv Vilela Pérez, Nicolás
Blanco Heras, Dora
Argüello Pedreira, Francisco
author Vilela Pérez, Nicolás
author_facet Vilela Pérez, Nicolás
Blanco Heras, Dora
Argüello Pedreira, Francisco
author_role author
author2 Blanco Heras, Dora
Argüello Pedreira, Francisco
author2_role author
author
dc.contributor.none.fl_str_mv Universidade de Santiago de Compostela. Centro de Investigación en Tecnoloxías Intelixentes da USC (CiTIUS)
Universidade de Santiago de Compostela. Departamento de Electrónica e Computación
dc.subject.none.fl_str_mv BAGAN
Classification
Data augmentation
EfficientNet
Multispectral
Residual generator
Transformer
Vegetation
Investigación
topic BAGAN
Classification
Data augmentation
EfficientNet
Multispectral
Residual generator
Transformer
Vegetation
Investigación
description Generative Adversarial Networks (GAN) can be used as a data augmentation technique in scenarios with limited labeled information and class imbalances, common issues in remote sensing datasets. The EfficientNet architecture has gained attention for achieving high accuracy with moderate computational cost. This work introduces EffBaGAN, a generative network specifically designed for the classification of multispectral remote sensing images based on EfficientNet, addressing data scarcity and class imbalances while minimizing network complexity. EffBaGAN is built upon a BAGAN architecture, incorporating a custom EfficientNet-based discriminator and generator. In particular, for the discriminator we propose RedEffDis, a reduced version of EfficientNet-B0 adapted to multispectral imagery. The generator, ResEffGen, includes a residual EfficientNet-based path, which enhances the quality of the generated synthetic samples. Additionally, a superpixel-based sample extraction procedure is used to further reduce the computational cost of the method. Experiments were conducted on large, very high-resolution multispectral images of vegetation, demonstrating that EffBaGAN achieves higher accuracy than other advanced classification methods, including vision transformers and residual BAGAN, while maintaining a significantly lower computational cost. In fact, EffBaGAN is more than twice as fast as the residual BAGAN, making it an efficient solution for remote sensing image classification in data-scarce environments.
publishDate 2024
dc.date.none.fl_str_mv 2024
2024-12-04
2024
2024-12-04
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/10347/38377
url https://hdl.handle.net/10347/38377
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Not available Not available
Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Not available Not available
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv IEEE
publisher.none.fl_str_mv IEEE
dc.source.none.fl_str_mv reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
instname:Universidad de Santiago de Compostela (USC)
instname_str Universidad de Santiago de Compostela (USC)
reponame_str Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
collection Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869425330874220544
score 15.811543

Similares en LA Referencia