Evaluating and Benchmarking Foundation Models for Earth Observation and Geospatial AI

TL;DR

This paper evaluates the performance of Foundation Models in Earth Observation and geospatial AI, demonstrating their label efficiency and proposing a benchmark for fair comparison across models.

Contribution

It introduces a new evaluation benchmark for Foundation Models in EO and shows their advantages over problem-specific models in limited data scenarios.

Findings

Foundation Models outperform problem-specific models with limited labeled data.

The proposed benchmark enables standardized comparison of EO Foundation Models.

Foundation Models are label efficient and effective for various EO tasks.

Abstract

When we are primarily interested in solving several problems jointly with a given prescribed high performance accuracy for each target application, then Foundation Models should for most cases be used rather than problem-specific models. We focus on the specific Computer Vision application of Foundation Models for Earth Observation (EO) and geospatial AI. These models can solve important problems we are tackling, including for example land cover classification, crop type mapping, flood segmentation, building density estimation, and road regression segmentation. In this paper, we show that for a limited number of labelled data, Foundation Models achieve improved performance compared to problem-specific models. In this work, we also present our proposed evaluation benchmark for Foundation Models for EO. Benchmarking the generalization performance of Foundation Models is important as it has become difficult to standardize a fair comparison across the many different models that have been proposed recently. We present the results using our evaluation benchmark for EO Foundation Models and show that Foundation Models are label efficient in the downstream tasks and help us solve problems we are tackling in EO and remote sensing.