|
|
--- |
|
|
datasets: |
|
|
- earth-insights/EarthReason |
|
|
base_model: |
|
|
- Qwen/Qwen2.5-VL-7B-Instruct |
|
|
library_name: transformers |
|
|
--- |
|
|
|
|
|
|
|
|
## Bridging Semantics and Geometry: A Decoupled LVLM–SAM Framework for Reasoning Segmentation in Remote Sensing |
|
|
|
|
|
This is the 7B model of [Think2Seg-RS](https://github.com/Ricardo-XZ/Think2Seg-RS), a decoupled framework for reasoning segmentation in remote sensing (RS) imagery. |
|
|
|
|
|
Our core idea is to decouple high-level semantic reasoning from low-level geometric execution. Specifically, we train an LVLM prompter (e.g., Qwen-2.5-VL) to control a frozen Segment Anything Model (SAM2) via structured geometric prompts. Through a result-oriented reinforcement learning objective, the LVLM learns to translate abstract semantic reasoning into spatially grounded actions, achieving state-of-the-art performance on the EarthReason dataset. |
|
|
|
|
|
For more details, code, and the complete framework, please visit our [GitHub repository](https://github.com/Ricardo-XZ/Think2Seg-RS). |
