Add pipeline and library tags, and enrich description for UAGLNet

This PR improves the model card for UAGLNet by:
- Adding the `pipeline_tag: image-segmentation` to correctly classify the model's task.
- Adding the `library_name: pytorch` based on clear evidence in the GitHub repository's `requirements.txt` and installation instructions.
- Enriching the main content with a concise description of the model, summarizing its key features.
- Ensuring the paper link remains an arXiv link, adhering to the instruction not to replace existing arXiv links.
- Removing the "File information" section, as it's not intended for the public model card.

Please review and merge if these improvements are satisfactory.

README.md

@@ -1,9 +1,13 @@
 ---
 license: apache-2.0
+pipeline_tag: image-segmentation
+library_name: pytorch
 ---
 
 # UAGLNet
 
+UAGLNet (Uncertainty-Aggregated Global-Local Fusion Network) is a model designed for building extraction from remote sensing images. It exploits high-quality global-local visual semantics under the guidance of uncertainty modeling, using a cooperative encoder with hybrid CNN and transformer layers.
+
 **Repository:** [https://github.com/Dstate/UAGLNet](https://github.com/Dstate/UAGLNet)
 
-**Paper:** *“UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction”* ([arXiv:2512.12941](https://arxiv.org/abs/2512.12941))
+**Paper:** *“UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction”* ([arXiv:2512.12941](https://arxiv.org/abs/2512.12941))