LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation

TL;DR

LHRS-Bot-Nova is a specialized multimodal large language model for remote sensing that integrates enhanced vision encoding, a novel bridge layer, and large-scale datasets to improve understanding and interpretation of Earth's surface imagery.

Contribution

The paper introduces LHRS-Bot-Nova with an improved vision encoder, a novel bridge layer, and new datasets for better remote sensing image understanding and instruction following.

Findings

Superior performance on remote sensing tasks

Effective spatial recognition and instruction following

Reliable benchmark results for model comparison

Abstract

Automatically and rapidly understanding Earth's surface is fundamental to our grasp of the living environment and informed decision-making. This underscores the need for a unified system with comprehensive capabilities in analyzing Earth's surface to address a wide range of human needs. The emergence of multimodal large language models (MLLMs) has great potential in boosting the efficiency and convenience of intelligent Earth observation. These models can engage in human-like conversations, serve as unified platforms for understanding images, follow diverse instructions, and provide insightful feedbacks. In this study, we introduce LHRS-Bot-Nova, an MLLM specialized in understanding remote sensing (RS) images, designed to expertly perform a wide range of RS understanding tasks aligned with human instructions. LHRS-Bot-Nova features an enhanced vision encoder and a novel bridge layer, enabling efficient visual compression and better language-vision alignment. To further enhance RS-oriented vision-language alignment, we propose a large-scale RS image-caption dataset, generated through feature-guided image recaptioning. Additionally, we introduce an instruction dataset specifically designed to improve spatial recognition abilities. Extensive experiments demonstrate superior performance of LHRS-Bot-Nova across various RS image understanding tasks. We also evaluate different MLLM performances in complex RS perception and instruction following using a complicated multi-choice question evaluation benchmark, providing a reliable guide for future model selection and improvement. Data, code, and models will be available at https://github.com/NJU-LHRS/LHRS-Bot.