Generalized Scalable Neighborhood Component Analysis for Single and Multi-Label Remote Sensing Image Characterization
![Thumbnail](/xmlui/bitstream/handle/10234/198762/81443.pdf.jpg?sequence=4&isAllowed=y)
Visualitza/
Metadades
Mostra el registre complet de l'elementcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/43662
comunitat-uji-handle3:10234/159451
comunitat-uji-handle4:
INVESTIGACIONMetadades
Títol
Generalized Scalable Neighborhood Component Analysis for Single and Multi-Label Remote Sensing Image CharacterizationData de publicació
2021Editor
IEEEISBN
9781665403696Cita bibliogràfica
KANG, Jian; FERNANDEZ-BELTRAN, Ruben; PLAZA, Antonio. Generalized Scalable Neighborhood Component Analysis for Single and Multi-Label Remote Sensing Image Characterization. In: 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. IEEE, 2021. p. 2150-2153.Tipus de document
info:eu-repo/semantics/conferenceObjectVersió
info:eu-repo/semantics/publishedVersionParaules clau / Matèries
Resum
Deep metric learning has recently become a prominent technology for the semantic understanding ofremote sensing (RS)
scenes due to its great potential for characterizing visual semantics. However, state-of-the-art ... [+]
Deep metric learning has recently become a prominent technology for the semantic understanding ofremote sensing (RS)
scenes due to its great potential for characterizing visual semantics. However, state-of-the-art deep metric learning models are often constrained in RS by the use of single-label annotations, which eventually reduce their capacity to characterize complex aerial scenes. Additionally, many of the existing works are specialized in particular RS applications which
constrains the study of their associated metric spaces from
a multi-task perspective. In this paper, we propose a new
unified deep metric learning approach for both single- and
multi-label RS scene characterization while also taking into
account different downstream RS applications. Specifically,
we extend the Scalable Neighborhood Component Analysis
(SNCA) to the multi-label case and propose its generalized
version, i.e., GSNCA. Extensive experiments on single- and
multi-label RS benchmark datasets have been conducted to
evaluate the effectiveness of the proposed method for RS image classification, clustering and retrieval. [-]
Descripció
Ponencia presentada en: IEEE International Symposium on Geoscience and Remote Sensing (IGARSS) 2021, del 11 al 16 de julio de 2021
Publicat a
IEEE, 2021. p. 2150-2153Drets d'accés
http://rightsstatements.org/vocab/InC/1.0/
info:eu-repo/semantics/openAccess
info:eu-repo/semantics/openAccess