RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts
This work addresses comprehensive vision understanding for remote sensing applications, offering a domain-specific solution that is incremental in improving existing models.
The authors tackled the lack of pixel-level understanding and multi-image handling in remote sensing vision-language models by proposing RSUniVLM, a unified model that achieves state-of-the-art performance across image-level, region-level, and pixel-level tasks, including change detection and captioning, while constraining parameters to about 1 billion.
Remote Sensing Vision-Language Models (RS VLMs) have made much progress in the tasks of remote sensing (RS) image comprehension. While performing well in multi-modal reasoning and multi-turn conversations, the existing models lack pixel-level understanding and struggle with multi-image inputs. In this work, we propose RSUniVLM, a unified, end-to-end RS VLM designed for comprehensive vision understanding across multiple granularity, including image-level, region-level, and pixel-level tasks. RSUniVLM also performs effectively in multi-image analysis, with instances of change detection and change captioning. To enhance the model's ability to capture visual information at different levels without increasing model size, we design a novel architecture called Granularity-oriented Mixture of Experts to constraint the model to about 1 billion parameters. We also construct a large-scale RS instruction-following dataset based on a variety of existing datasets in both RS and general domain, encompassing various tasks such as object localization, visual question answering, and semantic segmentation. Substantial experiments have been conducted to validate the superiority of the proposed RSUniVLM up to state-of-the-art across various RS tasks. Code and model will be available at \href{https://github.com/xuliu-cyber/RSUniVLM}{here}.