CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models

TL;DR

CHOICE is a comprehensive benchmark designed to evaluate the remote sensing capabilities of large vision-language models across perception and reasoning, addressing a critical gap in systematic assessment tools for Earth observation tasks.

Contribution

This paper introduces CHOICE, the first extensive benchmark with over 10,500 problems, for objectively evaluating the remote sensing abilities of VLMs across multiple dimensions.

Findings

Most VLMs show significant limitations in remote sensing tasks.

The benchmark reveals gaps in perception and reasoning capabilities of current models.

CHOICE provides a standardized platform for future model evaluation and development.

Abstract

The rapid advancement of Large Vision-Language Models (VLMs), both general-domain models and those specifically tailored for remote sensing, has demonstrated exceptional perception and reasoning capabilities in Earth observation tasks. However, a benchmark for systematically evaluating their capabilities in this domain is still lacking. To bridge this gap, we propose CHOICE, an extensive benchmark designed to objectively evaluate the hierarchical remote sensing capabilities of VLMs. Focusing on 2 primary capability dimensions essential to remote sensing: perception and reasoning, we further categorize 6 secondary dimensions and 23 leaf tasks to ensure a well-rounded assessment coverage. CHOICE guarantees the quality of all 10,507 problems through a rigorous process of data collection from 50 globally distributed cities, question construction and quality control. The newly curated data and the format of multiple-choice questions with definitive answers allow for an objective and straightforward performance assessment. Our evaluation of 3 proprietary and 21 open-source VLMs highlights their critical limitations within this specialized context. We hope that CHOICE will serve as a valuable resource and offer deeper insights into the challenges and potential of VLMs in the field of remote sensing. We will release CHOICE at [this https URL](https://github.com/ShawnAn-WHU/CHOICE).