GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates

doi:doi:10.57702/uap93zif

GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates

Land cover maps are a pivotal element in a wide range of Earth Observation (EO) applications. However, annotating large datasets to develop supervised systems for remote sensing (RS) semantic segmentation is costly and time-consuming. Unsupervised Domain Adaptation (UDA) could tackle these issues by adapting a model trained on a source domain, where labels are available, to a target domain, without annotations.

BibTex:

@dataset{Valerio_Marsocci_and_Simone_Scardapane_and_Nicolas_Gonthier_and_Anatol_Garioud_and_Clément_Mallet_2024,
    abstract = {Land cover maps are a pivotal element in a wide range of Earth Observation (EO) applications. However, annotating large datasets to develop supervised systems for remote sensing (RS) semantic segmentation is costly and time-consuming. Unsupervised Domain Adaptation (UDA) could tackle these issues by adapting a model trained on a source domain, where labels are available, to a target domain, without annotations.},
    author = {Valerio Marsocci and Simone Scardapane and Nicolas Gonthier and Anatol Garioud and Clément Mallet},
    doi = {10.57702/uap93zif},
    institution = {No Organization},
    keyword = {'geographical coordinates', 'remote sensing', 'semantic segmentation', 'unsupervised domain adaptation'},
    month = {dec},
    publisher = {TIB},
    title = {GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates},
    url = {https://service.tib.eu/ldmservice/dataset/geomultitasknet--remote-sensing-unsupervised-domain-adaptation-using-geographical-coordinates},
    year = {2024}
}