Identificador persistente para citar o vincular este elemento:
http://hdl.handle.net/10662/20332
Registro completo de Metadatos
Campo DC | Valor | idioma |
---|---|---|
dc.contributor.author | Paoletti Ávila, Mercedes Eugenia | - |
dc.contributor.author | Moreno Álvarez, Sergio | - |
dc.contributor.author | Haut Hurtado, Juan Mario | - |
dc.date.accessioned | 2024-02-07T12:50:38Z | - |
dc.date.available | 2024-02-07T12:50:38Z | - |
dc.date.issued | 2021 | - |
dc.identifier.issn | 0196-2892 | - |
dc.identifier.uri | http://hdl.handle.net/10662/20332 | - |
dc.description.abstract | The profound impact of deep learning and particularly of convolutional neural networks (CNNs) in automatic image processing has been decisive for the progress and evolution of remote sensing (RS) hyperspectral imaging (HSI) processing. Indeed, CNNs have stated themselves as the current state-ofart, reaching unparalleled results in HSI classification. However, most CNNs were designed for RGB images and their direct application to HSI data analysis could lead to nonoptimal solutions. Moreover, CNNs perform classification based on the identification of specific features, neglecting the spatialrelationships between different features (i.e., their arrangement) due to pooling techniques. The capsule network (CapsNet) architecture is an attempt to overcome this drawback by nesting several neural layers within a capsule, connected by dynamic routing, both to identify not only the presence of a feature, but also its instantiation parameters, and to learn the relationships between different features. Although this mechanism improves the data representations, enhancing the classification of HSI data, it still acts as a black box, without control of the most relevant features for classification purposes. Indeed, important features could be discriminated. In this paper, a new multiple attention guided CapsNet is proposed to improve feature processing for RSHSIs classification, both to improve computational efficiency (in terms of parameters) and to increase accuracy. Hence, the most representatives visual parts of the images are identified using a detailed feature extractor coupled with attention mechanisms. Extensive experimental results have been obtained on five real datasets, demonstrating the great potential of the proposed method compared to other state-of-the-art classifiers. | en_Us |
dc.description.sponsorship | This work was supported by in part Junta de Extremadura FEDER under Grant GR18060 and Grant GR21040 and by in part by 2021 Leonardo Grant for Researchers and Cultural Creators, BBVA Foundation. | - |
dc.format.extent | 20 p. | - |
dc.format.mimetype | application/pdf | en_US |
dc.language.iso | eng | es_ES |
dc.publisher | IEEE | - |
dc.rights | Atribución 4.0 Internacional | - |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | - |
dc.subject | Red de cápsulas | es_ES |
dc.subject | Redes neuronales convolucionales | es_ES |
dc.subject | Reportaje | es_ES |
dc.subject | HSI | es_ES |
dc.subject | Atención | es_ES |
dc.subject | Feature | en_Us |
dc.subject | Attention | en_Us |
dc.subject | Capsule network (CapsNet) | en_Us |
dc.subject | Convolutional neural networks (CNNs) | en_Us |
dc.title | Multiple attention-guided capsule networks for hyperspectral image classification | es_ES |
dc.type | article | es_ES |
dc.description.version | peerReviewed | es_ES |
europeana.type | TEXT | en_US |
dc.rights.accessRights | openAccess | es_ES |
dc.subject.unesco | 2490 Neurociencias | - |
dc.subject.unesco | 3304 Tecnología de Los Ordenadores | - |
europeana.dataProvider | Universidad de Extremadura. España | es_ES |
dc.identifier.bibliographicCitation | M. E. Paoletti, S. Moreno-Álvarez and J. M. Haut, "Multiple Attention-Guided Capsule Networks for Hyperspectral Image Classification," in IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-20, 2022, Art no. 5520420, doi: 10.1109/TGRS.2021.3135506 | - |
dc.type.version | publishedVersion | - |
dc.contributor.affiliation | Universidad de Extremadura. Departamento de Tecnología de los Computadores y de las Comunicaciones | es_ES |
dc.relation.publisherversion | https://ieeexplore.ieee.org/document/9650856 | - |
dc.identifier.doi | 10.1109/TGRS.2021.3135506 | - |
dc.identifier.publicationtitle | IEEE Transactions on Geoscience and Remote Sensing | - |
dc.identifier.publicationfirstpage | 5520420-1 | - |
dc.identifier.publicationlastpage | 5520420-20 | - |
dc.identifier.publicationvolume | 60 | es_ES |
dc.identifier.e-issn | 1558-0644 | - |
dc.identifier.orcid | 0000-0003-1030-3729 | es_ES |
dc.identifier.orcid | 0000-0001-6701-961X | es_ES |
dc.identifier.orcid | 0000-0002-1858-9920 | es_ES |
Colección: | DIEEA - Artículos DTCYC - Artículos |
Archivos
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
TGRS_2021_3135506.pdf | 6,34 MB | Adobe PDF | Descargar |
Este elemento está sujeto a una licencia Licencia Creative Commons