End-to-end Learning for Land Cover Classification using Irregular and Unaligned SITS by Combining Attention-Based Interpolation with Sparse Variational Gaussian Processes

Valentine Bellet (1, 2) , Mathieu Fauvel (1) , Jordi Inglada (1) , Julien Michel (1)

1 CESBIO - Centre d'études spatiales de la biosphère
2 UT - Université de Toulouse

Mots clés: Irregular Sampling; Satellite Image Time Series SITS; Sentinel-2; Land Cover Map; Classification; Large Scale; Sparse Variational Gaussian Processes; Earth Observation (EO); Remote Sensing

Domaines: Traitement du signal et de l'image [eess.SP]; Intelligence artificielle [cs.AI]; Ingénierie de l'environnement; Méthodes et statistiques; Machine Learning [stat.ML]

Valentine Bellet, Mathieu Fauvel, Jordi Inglada, Julien Michel. End-to-end Learning for Land Cover Classification using Irregular and Unaligned SITS by Combining Attention-Based Interpolation with Sparse Variational Gaussian Processes. 2023. ⟨hal-04112115v1⟩