Semisupervised learning techniques are gaining popularity due to their capability of building models that are effective, even when scarce amounts of labeled data are available. In this letter, we present a framework and specific tasks for self-supervised pretraining of multichannel models, such as the fusion of multispectral and synthetic aperture radar (SAR) images. We show that the proposed self-supervised approach is highly effective at learning features that correlate with the labels for land cover classification. This is enabled by an explicit design of pretraining tasks which promotes bridging the gaps between sensing modalities and exploiting the spectral characteristics of the input. In a semisupervised setting, when limited labels are available, using the proposed self-supervised pretraining, followed by supervised fine-tuning for land cover classification with SAR and multispectral data, outperforms conventional approaches such as purely supervised learning, initialization from training on ImageNet, and other recent self-supervised approaches.

Semi-Supervised Learning for Joint SAR and Multispectral Land Cover Classification / Montanaro, Antonio; Valsesia, Diego; Fracastoro, Giulia; Magli, Enrico. - In: IEEE GEOSCIENCE AND REMOTE SENSING LETTERS. - ISSN 1545-598X. - STAMPA. - 19:(2022), pp. 1-5. [10.1109/lgrs.2022.3195259]

Semi-Supervised Learning for Joint SAR and Multispectral Land Cover Classification

Antonio Montanaro;Diego Valsesia;Giulia Fracastoro;Enrico Magli
2022

Abstract

Semisupervised learning techniques are gaining popularity due to their capability of building models that are effective, even when scarce amounts of labeled data are available. In this letter, we present a framework and specific tasks for self-supervised pretraining of multichannel models, such as the fusion of multispectral and synthetic aperture radar (SAR) images. We show that the proposed self-supervised approach is highly effective at learning features that correlate with the labels for land cover classification. This is enabled by an explicit design of pretraining tasks which promotes bridging the gaps between sensing modalities and exploiting the spectral characteristics of the input. In a semisupervised setting, when limited labels are available, using the proposed self-supervised pretraining, followed by supervised fine-tuning for land cover classification with SAR and multispectral data, outperforms conventional approaches such as purely supervised learning, initialization from training on ImageNet, and other recent self-supervised approaches.
File in questo prodotto:
File Dimensione Formato  
Semi-Supervised_Learning_for_Joint_SAR_and_Multispectral_Land_Cover_Classification.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.45 MB
Formato Adobe PDF
1.45 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Self_supervised_multispectral_segmentation.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 1.04 MB
Formato Adobe PDF
1.04 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

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/11583/2977422