Any Model, Any Place, Any Time: Get Remote Sensing Foundation Model Embeddings On Demand

TL;DR

The paper introduces rs-embed, a Python library that simplifies access to remote sensing foundation model embeddings across different models, formats, and data specifications, facilitating easier adoption and benchmarking.

Contribution

It presents a unified, ROI-centric interface for obtaining remote sensing embeddings from any supported model, streamlining large-scale processing and comparison.

Findings

Enables single-line retrieval of embeddings from multiple models

Supports efficient batch processing for large datasets

Facilitates fair benchmarking across diverse models

Abstract

The remote sensing community is witnessing a rapid growth of foundation models, which provide powerful embeddings for a wide range of downstream tasks. However, practical adoption and fair comparison remain challenging due to substantial heterogeneity in model release formats, platforms and interfaces, and input data specifications. These inconsistencies significantly increase the cost of obtaining, using, and benchmarking embeddings across models. To address this issue, we propose rs-embed, a Python library that offers a unified, region of interst (ROI) centric interface: with a single line of code, users can retrieve embeddings from any supported model for any location and any time range. The library also provides efficient batch processing to enable large-scale embedding generation and evaluation. The code is available at: https://github.com/cybergis/rs-embed