Abstract
The multimodal fusion of images and scene captions has been extensively explored and applied in various fields. However, when dealing with complex remote sensing (RS) scenes, existing studies have predominantly concentrated on architectural optimizations for integrating textual semantic information with visual features, while largely neglecting the generation of high-quality RS captions and the investigation of their effectiveness in multimodal semantic this http URL this context, we propose the Dynamic MLLM Mixture-of-Experts Perception-Guided Remote Sensing Scene Segmentation, referred to as this http URL design multiple prompts for MLLMs to generate high-quality RS captions, enabling MLLMs to perceive RS scenes from diverse expert perspectives. DINOv3 is employed to extract dense visual representations of this http URL design a Dynamic MixExperts module that adaptively integrates the most effective textual semantics. Linguistic Query Guided Attention is constructed to utilize textual semantic information to guide visual features for precise segmentation. The MLLMs include LLaVA, ChatGPT, and Qwen. Our method achieves superior performance on three public semantic segmentation RS datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2605.10769
