GRASP: Guided Region-Aware Sparse Prompting for Adapting MLLMs to Remote Sensing
This addresses the challenge of improving MLLM effectiveness in remote sensing tasks, which is an incremental advance in domain-specific fine-tuning.
The paper tackled the problem of adapting Multimodal Large Language Models to remote sensing images, which suffer from large-scale variations and sparse targets, by proposing GRASP, a parameter-efficient fine-tuning strategy that achieved competitive performance on multiple RSVQA benchmarks.
In recent years, Multimodal Large Language Models (MLLMs) have made significant progress in visual question answering tasks. However, directly applying existing fine-tuning methods to remote sensing (RS) images often leads to issues such as overfitting on background noise or neglecting target details. This is primarily due to the large-scale variations, sparse target distributions, and complex regional semantic features inherent in RS images. These challenges limit the effectiveness of MLLMs in RS tasks. To address these challenges, we propose a parameter-efficient fine-tuning (PEFT) strategy called Guided Region-Aware Sparse Prompting (GRASP). GRASP introduces spatially structured soft prompts associated with spatial blocks extracted from a frozen visual token grid. Through a question-guided sparse fusion mechanism, GRASP dynamically aggregates task-specific context into a compact global prompt, enabling the model to focus on relevant regions while filtering out background noise. Extensive experiments on multiple RSVQA benchmarks show that GRASP achieves competitive performance compared to existing fine-tuning and prompt-based methods while maintaining high parameter efficiency.