EarthView : a large scale remote sensing dataset for self-supervision
Velazquez Dorta, Diego Alejandro (Centre de Visió per Computador)
Rodríguez López, Pau (Centre de Visió per Computador)
Alonso Muñoz, Sergio (Satellogic)
Gonfaus Sitjes, Josep Maria (Satellogic)
Gonzàlez, Jordi (Centre de Visió per Computador)
Richarte, Gerardo (Satellogic)
Marin, Javier (Satellogic)
Bengio, Yoshua (Université de Montréal. MILA)
Lacoste, Alexandre (ServiceNow Research)

Publicació:	IEEE, 2025
Descripció:	10 pàg.
Resum:	This paper presents EarthView, a comprehensive dataset specifically designed for self-supervision on remote sensing data, intended to enhance deep learning applications on Earth monitoring tasks. The dataset spans 15 tera pixels of global remote-sensing data, combining imagery from a diverse range of sources, including NEON, Sentinel, and a novel release of 1m spatial resolution data from Satellogic. Our dataset provides a wide spectrum of image data with varying resolutions, harnessed from different sensors and organized coherently into an accessible HuggingFace dataset in parquet format. This data spans five years, from 2017 to 2022. Accompanying the dataset, we introduce EarthMAE, a tailored Masked Autoencoder, developed to tackle the distinct challenges of remote sensing data. Trained in a self-supervised fashion, EarthMAE effectively processes different data modalities such as hyperspectral, multispectral, topographical data, segmentation maps, and temporal structure. This model helps us show that pre-training on Satellogic data improves performance on downstream tasks. While there is still a gap to fill in MAE for heterogeneous data, we regard this innovative combination of an expansive, diverse dataset and a versatile model adapted for self-supervised learning as a stride forward in deep learning for Earth monitoring.
Drets:	Aquest material està protegit per drets d'autor i/o drets afins. Podeu utilitzar aquest material en funció del que permet la legislació de drets d'autor i drets afins d'aplicació al vostre cas. Per a d'altres usos heu d'obtenir permís del(s) titular(s) de drets.
Llengua:	Anglès
Document:	Capítol de llibre ; recerca ; Versió acceptada per publicar
Matèria:	Earth ; Deep learning ; Training ; Adaptation models ; Self-supervised learning ; Sensors ; Spatial resolution ; Remote sensing ; Monitoring ; Sensor arrays
Publicat a:	2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), 2025, p. 1138-1147, ISBN 979-8-3315-3662-6

DOI: 10.1109/WACVW65960.2025.00136

Disponible a partir de: 2027-12-30 Postprint

El registre apareix a les col·leccions:
Llibres i col·leccions > Capítols de llibres