Data from satellites or aerial vehicles are most of the times unlabelled. Annotating such data accurately is difficult, requires expertise, and is costly in terms of time. Even if Earth Observation (EO) data were correctly labelled, labels might change over time. Learning from unlabelled data within a semi-supervised learning framework for segmentation of aerial images is challenging. In this paper, we develop a new model for semantic segmentation of unlabelled images, the Non-annotated Earth Observation Semantic Segmentation (NEOS) model. NEOS performs domain adaptation as the target domain does not have ground truth masks. The distribution inconsistencies between the target and source domains are due to differences in acquisition scenes, environment conditions, sensors, and times. Our model aligns the learned representations of the different domains to make them coincide. The evaluation results show that it is successful and outperforms other models for semantic segmentation of unlabelled data.
Learning from Unlabelled data with Transformers: Domain Adaptation for Semantic Segmentation of High Resolution Aerial Images / Dionelis, N.; Pro, F.; Maiano, L.; Amerini, I.; Saux, B. L.. - (2024), pp. 8167-8172. (Intervento presentato al convegno 2024 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2024 tenutosi a Athens; Greece) [10.1109/IGARSS53475.2024.10641541].
Learning from Unlabelled data with Transformers: Domain Adaptation for Semantic Segmentation of High Resolution Aerial Images
Pro F.
;Maiano L.
;Amerini I.
;
2024
Abstract
Data from satellites or aerial vehicles are most of the times unlabelled. Annotating such data accurately is difficult, requires expertise, and is costly in terms of time. Even if Earth Observation (EO) data were correctly labelled, labels might change over time. Learning from unlabelled data within a semi-supervised learning framework for segmentation of aerial images is challenging. In this paper, we develop a new model for semantic segmentation of unlabelled images, the Non-annotated Earth Observation Semantic Segmentation (NEOS) model. NEOS performs domain adaptation as the target domain does not have ground truth masks. The distribution inconsistencies between the target and source domains are due to differences in acquisition scenes, environment conditions, sensors, and times. Our model aligns the learned representations of the different domains to make them coincide. The evaluation results show that it is successful and outperforms other models for semantic segmentation of unlabelled data.File | Dimensione | Formato | |
---|---|---|---|
Dionelis_postprint_Learning_2024.pdf
accesso aperto
Note: DOI: 10.1109/IGARSS53475.2024.10641541 - http://arxiv.org/pdf/2404.11299
Tipologia:
Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
4.37 MB
Formato
Adobe PDF
|
4.37 MB | Adobe PDF | |
Dionelis_Learning_2024.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
5.07 MB
Formato
Adobe PDF
|
5.07 MB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.