Publicación:
Self-Supervised Learning on Small In-Domain Datasets Can Overcome Supervised Learning in Remote Sensing

Vista sencilla de ítem
dc.contributor.authorSanchez-Fernandez, Andres J.
dc.contributor.authorMoreno Álvarez, Sergio
dc.contributor.authorRico Gallego, Juan Antonio
dc.contributor.authorTabik, Siham
dc.contributor.orcidhttps://orcid.org/0000-0001-6743-3570
dc.contributor.orcidhttps://orcid.org/0000-0002-4264-7473
dc.contributor.orcidhttps://orcid.org/0000-0003-4093-5356
dc.date.accessioned2024-11-20T10:12:41Z
dc.date.available2024-11-20T10:12:41Z
dc.date.issued2024
dc.descriptionThe registered version of this article, first published in “IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17", is available online at the publisher's website: IEEE, https://doi.org/10.1109/JSTARS.2024.3421622 La versión registrada de este artículo, publicado por primera vez en “IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17", está disponible en línea en el sitio web del editor: IEEE, https://doi.org/10.1109/JSTARS.2024.3421622
dc.description.abstractThe availability of high-resolution satellite images has accelerated the creation of new datasets designed to tackle broader remote sensing (RS) problems. Although popular tasks, such as scene classification, have received significant attention, the recent release of the Land-1.0 RS dataset marks the initiation of endeavors to estimate land-use and land-cover (LULC) fraction values per RGB satellite image. This challenging problem involves estimating LULC composition, i.e., the proportion of different LULC classes from satellite imagery, with major applications in environmental monitoring, agricultural/urban planning, and climate change studies. Currently, supervised deep learning models—the state-of-the-art in image classification—require large volumes of labeled training data to provide good generalization. To face the challenges posed by the scarcity of labeled RS data, self-supervised learning (SSL) models have recently emerged, learning directly from unlabeled data by leveraging the underlying structure. This is the first article to investigate the performance of SSL in LULC fraction estimation on RGB satellite patches using in-domain knowledge. We also performed a complementary analysis on LULC scene classification. Specifically, we pretrained Barlow Twins, MoCov2, SimCLR, and SimSiam SSL models with ResNet-18 using the Sentinel2GlobalLULC small RS dataset and then performed transfer learning to downstream tasks on Land-1.0. Our experiments demonstrate that SSL achieves competitive or slightly better results when trained on a smaller high-quality in-domain dataset of 194 877 samples compared to the supervised model trained on ImageNet-1k with 1 281 167 samples. This outcome highlights the effectiveness of SSL using in-distribution datasets, demonstrating efficient learning with fewer but more relevant data.en
dc.description.versionversión publicada
dc.identifier.citationA. J. Sanchez-Fernandez, S. Moreno-Álvarez, J. A. Rico-Gallego and S. Tabik, "Self-Supervised Learning on Small In-Domain Datasets Can Overcome Supervised Learning in Remote Sensing," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, pp. 12797-12810, 2024, doi: 10.1109/JSTARS.2024.3421622
dc.identifier.doihttps://doi.org/10.1109/JSTARS.2024.3421622
dc.identifier.issn1939-1404 | eISSN 2151-1535
dc.identifier.urihttps://hdl.handle.net/20.500.14468/24444
dc.journal.titleIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
dc.journal.volume17
dc.language.isoen
dc.page.final12810
dc.page.initial12797
dc.publisherIEEE
dc.relation.centerFacultades y escuelas::E.T.S. de Ingeniería Informática
dc.relation.departmentLenguajes y Sistemas Informáticos
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/deed.es
dc.subject12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informática
dc.subject.keywordsTask analysisen
dc.subject.keywordsEstimationen
dc.subject.keywordsScene classificationen
dc.subject.keywordsSatellitesen
dc.subject.keywordsSatellite Imagesen
dc.subject.keywordsDeep learningen
dc.subject.keywordsComputational modelingen
dc.subject.keywordsClimate changeen
dc.subject.keywordsRemote sensingen
dc.subject.keywordsSelf-supervised learningen
dc.subject.keywordsLand use planningen
dc.titleSelf-Supervised Learning on Small In-Domain Datasets Can Overcome Supervised Learning in Remote Sensingen
dc.typeartículoes
dc.typejournal articleen
dspace.entity.typePublication
relation.isAuthorOfPublication3482d7bc-e120-48a3-812e-cc4b25a6d2fe
relation.isAuthorOfPublication.latestForDiscovery3482d7bc-e120-48a3-812e-cc4b25a6d2fe
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
MorenoAlvarez_Sergio_2024SelfSupervisedLearni.pdf
Tamaño:
2.18 MB
Formato:
Adobe Portable Document Format
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
3.62 KB
Formato:
Item-specific license agreed to upon submission
Descripción:
Descargar
Colecciones
Artículos y papers