# GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Models

Source: [GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Models](<https://www.sota2.com/research/paper/68fa78e81e209131cea7b213>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:17.178Z

Authors: Gilles Quentin Hacheme, Girmaw Abebe Tadesse, Caleb Robinson, Akram Zaytar, Rahul Dodhia, Juan M. Lavista Ferres

Published: 2025-05-30T08:32:37.000Z

## Abstract

Classifying geospatial imagery remains a major bottleneck for applications such as disaster response and land-use monitoring-particularly in regions where annotated data is scarce or unavailable. Existing tools (e.g., RS-CLIP) that claim zero-shot classification capabilities for satellite imagery nonetheless rely on task-specific pretraining and adaptation to reach competitive performance. We introduce GeoVision Labeler (GVL), a strictly zero-shot classification framework: a vision Large Language Model (vLLM) generates rich, human-readable image descriptions, which are then mapped to user-defined classes by a conventional Large Language Model (LLM). This modular, and interpretable pipeline enables flexible image classification for a large range of use cases. We evaluated GVL across three benchmarks-SpaceNet v7, UC Merced, and RESISC45. It achieves up to 93.2% zero-shot accuracy on the binary Buildings vs. No Buildings task on SpaceNet v7. For complex multi-class classification tasks (UC Merced, RESISC45), we implemented a recursive LLM-driven clustering to form meta-classes at successive depths, followed by hierarchical classification-first resolving coarse groups, then finer distinctions-to deliver competitive zero-shot performance. GVL is open-sourced at https://github.com/microsoft/geo-vision-labeler to catalyze adoption in real-world geospatial workflows.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.24340>)

[PDF](<https://arxiv.org/pdf/2505.24340.pdf>)
