High-Rankness Regularized Semi-Supervised Deep Metric Learning for Remote Sensing Imagery
Ver/ Abrir
Impacto
Scholar |
Otros documentos de la autoría: kang, jian; Fernandez-Beltran, Ruben; Ye, Zhen; Tong, Xiaohua; Ghamisi, Pedram; Plaza, Antonio
Metadatos
Mostrar el registro completo del ítemcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/8013
comunitat-uji-handle3:10234/8014
comunitat-uji-handle4:
INVESTIGACIONMetadatos
Título
High-Rankness Regularized Semi-Supervised Deep Metric Learning for Remote Sensing ImageryAutoría
Fecha de publicación
2020Editor
MDPIISSN
2072-4292Cita bibliográfica
KANG, Jian, et al. High-Rankness Regularized Semi-Supervised Deep Metric Learning for Remote Sensing Imagery. Remote Sensing, 2020, vol. 12, núm. 16, p. 2603Tipo de documento
info:eu-repo/semantics/articleVersión de la editorial
https://www.mdpi.com/2072-4292/12/16/2603Versión
info:eu-repo/semantics/publishedVersionPalabras clave / Materias
Resumen
Deep metric learning has recently received special attention in the field of remote sensing (RS) scene characterization, owing to its prominent capabilities for modeling distances among RS images based on their semantic ... [+]
Deep metric learning has recently received special attention in the field of remote sensing (RS) scene characterization, owing to its prominent capabilities for modeling distances among RS images based on their semantic information. Most of the existing deep metric learning methods exploit pairwise and triplet losses to learn the feature embeddings with the preservation of semantic-similarity, which requires the construction of image pairs and triplets based on the supervised information (e.g., class labels). However, generating such semantic annotations becomes a completely unaffordable task in large-scale RS archives, which may eventually constrain the availability of sufficient training data for this kind of models. To address this issue, we reformulate the deep metric learning scheme in a semi-supervised manner to effectively characterize RS scenes. Specifically, we aim at learning metric spaces by utilizing the supervised information from a small number of labeled RS images and exploring the potential decision boundaries for massive sets of unlabeled aerial scenes. In order to reach this goal, a joint loss function, composed of a normalized softmax loss with margin and a high-rankness regularization term, is proposed, as well as its corresponding optimization algorithm. The conducted experiments (including different state-of-the-art methods and two benchmark RS archives) validate the effectiveness of the proposed approach for RS image classification, clustering and retrieval tasks. The codes of this paper are publicly available. [-]
Publicado en
Remote Sensing, 2020, vol. 12, núm. 16, p. 2603Proyecto de investigación
This work was supported in part by the National Key Research and Development Project of Chinaunder Grant 2018YFB0505400 and Grant 2017YFB0502700, in part by the National Natural Science Foundation ofChina under Grant 41631178, in part by the Spanish Ministry of Economy under Grant RTI2018-098651-B-C54, n part by FEDER-Junta de Extremadura under Grant GR18060, and in part by the European Union under theH2020 EOXPOSURE Project under Grant 734541.Derechos de acceso
info:eu-repo/semantics/openAccess
Aparece en las colecciones
- INIT_Articles [754]
- COM_Articles [824]
El ítem tiene asociados los siguientes ficheros de licencia:
Excepto si se señala otra cosa, la licencia del ítem se describe como: © 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open accessarticle distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).