Add pipeline tag, library name, and paper link

README.md

@@ -1,19 +1,22 @@
 ---
-license: mit
+base_model:
+- openmmlab/upernet-swin-tiny
 datasets:
 - heig-vd-geo/GridNet-HD
 language:
 - en
+license: mit
 metrics:
 - mean_iou
-base_model:
-- openmmlab/upernet-swin-tiny
+library_name: transformers
+pipeline_tag: image-segmentation
 ---
+
 # GridNet-HD Baseline: Image semantic segmentation and LiDAR projection framework
 
 ## Overview
 
-This repository provides a reproducible implementation of a semantic segmentation pipeline and 3D projection baseline used in our NeurIPS submission introducing the **GridNet-HD** dataset. The framework includes:
+This repository provides a reproducible implementation of a semantic segmentation pipeline and 3D projection baseline used in the paper [GridNet-HD: A High-Resolution Multi-Modal Dataset for LiDAR-Image Fusion on Power Line Infrastructure](https://huggingface.co/papers/2601.13052). The framework includes:
 
 * A semantic segmentation pipeline transformer-based with `UperNetForSemanticSegmentation` (via HuggingFace Transformers).
 * Support for high-resolution aerial imagery using random crop during training and sliding window inference at test time.
@@ -334,7 +337,4 @@ If you use this repo in research, please cite:
       eprint={2601.13052},
       url={https://arxiv.org/abs/2601.13052}, 
 }
-```
-
-
-
+```