LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model
This work addresses the need for better RS image understanding in AI applications, though it appears incremental by tailoring existing MLLM approaches to a specific domain.
The paper tackles the problem of inadequate consideration of diverse geographical landscapes and objects in remote sensing (RS) imagery by existing multimodal large language models (MLLMs), resulting in LHRS-Bot, an MLLM that exhibits profound understanding and nuanced reasoning in RS images, as demonstrated through comprehensive experiments.
The revolutionary capabilities of large language models (LLMs) have paved the way for multimodal large language models (MLLMs) and fostered diverse applications across various specialized domains. In the remote sensing (RS) field, however, the diverse geographical landscapes and varied objects in RS imagery are not adequately considered in recent MLLM endeavors. To bridge this gap, we construct a large-scale RS image-text dataset, LHRS-Align, and an informative RS-specific instruction dataset, LHRS-Instruct, leveraging the extensive volunteered geographic information (VGI) and globally available RS images. Building on this foundation, we introduce LHRS-Bot, an MLLM tailored for RS image understanding through a novel multi-level vision-language alignment strategy and a curriculum learning method. Additionally, we introduce LHRS-Bench, a benchmark for thoroughly evaluating MLLMs' abilities in RS image understanding. Comprehensive experiments demonstrate that LHRS-Bot exhibits a profound understanding of RS images and the ability to perform nuanced reasoning within the RS domain.