RT Book,_Section
T1 GAN-based data augmentation for the classification of remote sensing multispectral images
A1 Barreiro, Víctor
A1 Goldar Dieste, Álvaro
A1 Blanco Heras, Dora
A1 Argüello Pedreira, Francisco
K1 Data augmentation
K1 GAN
K1 Multispectral
K1 Classification
AB Multispectral images frequently suffer from limited labeled data, which constrains the accuracy of classification. The objective of data augmentation is to improve the performance of machine learning models by artificially increasing the size of the training dataset. This paper introduces mDAGAN, a data augmentation method for the classification of high resolution multispectral remote sensing images. It is an adaptation of DAGAN (Data Augmentation GAN) tomultispectral images, a generative adversarial network that consists of a generator and a discriminator. The augmentation capacity of mDAGAN for three differentclassical supervised classification algorithms has been evaluated over three high resolution multispectral images of vegetation, providing increased classification accuracies.
PB Sociedad de Arquitectura y Tecnología de Computadores (SARTECO)
SN 978-84-09-61749-4
YR 2024
FD 2024-06-17
LK http://hdl.handle.net/10347/34113
UL http://hdl.handle.net/10347/34113
LA eng
NO Barreiro, V.X., Goldar, Á., Blanco, D., Argüello, F. (2024). GAN-based data augmentation for the classification of remote sensing multispectral images. In: Avances en Arquitectura y Tecnología de Computadores. Actas de las Jornadas SARTECO, 83-87. A Coruña, España. ISBN: 978-84-09-61749-4
DS Minerva
RD 27 abr 2026