Towards Efficient Benchmarking of Foundation Models in Remote Sensing: A Capabilities Encoding Approach

TL;DR

This paper introduces a capabilities encoding approach to efficiently predict the performance of remote sensing foundation models across various tasks, simplifying model selection without extensive fine-tuning.

Contribution

It presents a novel, cost-effective method for benchmarking foundation models in remote sensing, enabling performance prediction without task-specific fine-tuning.

Findings

Capabilities encoding accurately predicts model performance

Simplifies selection of foundation models for new tasks

Provides insights for future remote sensing research

Abstract

Foundation models constitute a significant advancement in computer vision: after a single, albeit costly, training phase, they can address a wide array of tasks. In the field of Earth observation, over 75 remote sensing vision foundation models have been developed in the past four years. However, none has consistently outperformed the others across all available downstream tasks. To facilitate their comparison, we propose a cost-effective method for predicting a model's performance on multiple downstream tasks without the need for fine-tuning on each one. This method is based on what we call "capabilities encoding." The utility of this novel approach is twofold: we demonstrate its potential to simplify the selection of a foundation model for a given new task, and we employ it to offer a fresh perspective on the existing literature, suggesting avenues for future research. Codes are available at https://github.com/pierreadorni/capabilities-encoding.