BigEarthNet.txt: A Large-Scale Multi-Sensor Image-Text Dataset and Benchmark for Earth Observation

TL;DR

BigEarthNet.txt is a comprehensive large-scale multi-sensor Earth observation dataset with diverse annotations, designed to improve vision-language models' performance on remote sensing tasks.

Contribution

It introduces a novel, richly annotated multi-sensor dataset for Earth observation, enabling instruction-driven learning and benchmarking for remote sensing applications.

Findings

BigEarthNet.txt surpasses existing datasets in textual richness and annotation diversity.

Fine-tuning models on BigEarthNet.txt improves performance across multiple tasks.

Benchmark results reveal current models' limitations on complex land-use/land-cover classes.

Abstract

Vision-langugage models (VLMs) have shown strong performance in computer vision (CV), yet their performance on remote sensing (RS) data remains limited due to the lack of large-scale, multi-sensor RS image-text datasets with diverse textual annotations. Existing datasets predominantly include aerial Red-Green-Blue imagery, with short or weakly grounded captions, and provide limited diversity in annotation types. To address this limitation, we introduce BigEarthNet$.$txt, a large-scale, multi-sensor image-text dataset designed to advance instruction-driven image-text learning in Earth observation across multiple tasks. BigEarthNet$.$txt contains 464044 co-registered Sentinel-1 synthetic aperture radar and Sentinel-2 multispectral images with 9.6M text annotations, including: i) geographically anchored captions describing land-use/land-cover (LULC) classes, their spatial relations, and environmental context; ii) visual question answering pairs relevant for different tasks; and iii) referring expression detection instructions for bounding box prediction. Through a comparative statistical analysis, we demonstrate that BigEarthNet$.$txt surpasses existing RS image-text datasets in textual richness and annotation type variety. We further establish a manually-verified benchmark split to evaluate VLMs in RS and CV. The results show the limitations of these models on tasks that involve complex LULC classes, whereas fine-tuning using BigEarthNet$.$txt results in consistent performance gains across all considered tasks.