Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.08111 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913649412538368 |
|---|---|
| author | Velazquez, Diego López, Pau Rodriguez Alonso, Sergio Gonfaus, Josep M. Gonzalez, Jordi Richarte, Gerardo Marin, Javier Bengio, Yoshua Lacoste, Alexandre |
| author_facet | Velazquez, Diego López, Pau Rodriguez Alonso, Sergio Gonfaus, Josep M. Gonzalez, Jordi Richarte, Gerardo Marin, Javier Bengio, Yoshua Lacoste, Alexandre |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_08111 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EarthView: A Large Scale Remote Sensing Dataset for Self-Supervision Velazquez, Diego López, Pau Rodriguez Alonso, Sergio Gonfaus, Josep M. Gonzalez, Jordi Richarte, Gerardo Marin, Javier Bengio, Yoshua Lacoste, Alexandre Computer Vision and Pattern Recognition 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. |
| title | EarthView: A Large Scale Remote Sensing Dataset for Self-Supervision |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.08111 |