Land cover maps are a pivotal element in a wide range of Earth Observation (EO) applications. However, anno- tating large datasets to develop supervised systems for re- mote sensing (RS) semantic segmentation is costly and time- consuming. Unsupervised Domain Adaption (UDA) could tackle these issues by adapting a model trained on a source domain, where labels are available, to a target domain, without annotations. UDA, while gaining importance in computer vision, is still under-investigated in RS. Thus, we propose a new lightweight model, GeoMultiTaskNet, based on two contributions: a GeoMultiTask module (GeoMT), which utilizes geographical coordinates to align the source and target domains, and a Dynamic Class Sampling (DCS) strategy, to adapt the semantic segmentation loss to the fre- quency of classes. This approach is the first to use geo- graphical metadata for UDA in semantic segmentation. It reaches state-of-the-art performances (47,22% mIoU), re- ducing at the same time the number of parameters (33M), on a subset of the FLAIR dataset, a recently proposed dataset properly shaped for RS UDA, used for the first time ever for research scopes here.

GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates / Marsocci, Valerio; Gonthier, Nicolas; Garioud, Anatol; Scardapane, Simone; Mallet, Clément. - (2023), pp. 2075-2085. (Intervento presentato al convegno 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) tenutosi a Vancouver, Canada) [10.1109/cvprw59228.2023.00201].

GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates

Marsocci, Valerio
;
Scardapane, Simone;
2023

Abstract

Land cover maps are a pivotal element in a wide range of Earth Observation (EO) applications. However, anno- tating large datasets to develop supervised systems for re- mote sensing (RS) semantic segmentation is costly and time- consuming. Unsupervised Domain Adaption (UDA) could tackle these issues by adapting a model trained on a source domain, where labels are available, to a target domain, without annotations. UDA, while gaining importance in computer vision, is still under-investigated in RS. Thus, we propose a new lightweight model, GeoMultiTaskNet, based on two contributions: a GeoMultiTask module (GeoMT), which utilizes geographical coordinates to align the source and target domains, and a Dynamic Class Sampling (DCS) strategy, to adapt the semantic segmentation loss to the fre- quency of classes. This approach is the first to use geo- graphical metadata for UDA in semantic segmentation. It reaches state-of-the-art performances (47,22% mIoU), re- ducing at the same time the number of parameters (33M), on a subset of the FLAIR dataset, a recently proposed dataset properly shaped for RS UDA, used for the first time ever for research scopes here.
2023
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
remote sensing; domain adaptation; unsupervised domain adaptation; neural networks
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates / Marsocci, Valerio; Gonthier, Nicolas; Garioud, Anatol; Scardapane, Simone; Mallet, Clément. - (2023), pp. 2075-2085. (Intervento presentato al convegno 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) tenutosi a Vancouver, Canada) [10.1109/cvprw59228.2023.00201].
File allegati a questo prodotto
File Dimensione Formato  
Marsocci_GeoMultiTaskNet_2023.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 7.85 MB
Formato Adobe PDF
7.85 MB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1702038
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact