Unlocking Multi-Spectral Data for Multi-Modal Models with Guided Inputs and Chain-of-Thought Reasoning

TL;DR

This paper presents a training-free method to incorporate multi-spectral data into RGB-only large multimodal models, significantly improving remote sensing task performance through inference-time adaptations and reasoning instructions.

Contribution

It introduces a novel inference pipeline approach that enables multi-spectral data integration into existing RGB models without retraining, enhancing their applicability in remote sensing.

Findings

Achieved strong zero-shot performance gains on remote sensing benchmarks.

Demonstrated the effectiveness of guided inputs and Chain-of-Thought reasoning.

Enabled geospatial professionals to leverage generalist models for specialized sensor data.

Abstract

Multi-spectral imagery is a valuable input signal for Remote Sensing applications, such as land-use and land-cover classification and environmental monitoring. However, generalist Large Multi-modal Models (LMMs) are typically trained on RGB images, limiting their applicability to the RGB domain. At the same time, training multi-spectral multi-modal models is expensive and produces uniquely specialized models. To address this, we propose a novel training-free approach that introduces multi-spectral data within the inference pipeline of standard RGB-only LMMs, allowing large gains in performance. Our approach leverages the LMMs' understanding of the visual space by adapting non-RGB inputs to that space and injecting domain-specific information and Chain-of-Thought reasoning as instructions. We demonstrate this with the Gemini 2.5 model and observe strong Zero-Shot performance gains on popular Remote Sensing benchmarks. These results highlight the potential for geospatial professionals to leverage powerful generalist models for specialized sensor inputs, benefiting from rich reasoning capabilities grounded in specialized data.