Update README.md

README.md

@@ -5,10 +5,9 @@ language:
 library_name: open_clip
 pipeline_tag: image-segmentation
 ---
-# SAN
-**Side Adapter Network for Open-Vocabulary Semantic Segmentation**
+<h1 align="center"> Side Adapter Network for Open-Vocabulary Semantic Segmentation</h1>
 
-[Github](https://github.com/MendelXu/SAN)|[Demo](https://huggingface.co/spaces/Mendel192/san_demo)
+<div align="center"><a href="https://arxiv.org/abs/2302.12242">Paper</a> | <a href="https://github.com/MendelXu/SAN">Code</a> | <a href="https://huggingface.co/spaces/Mendel192/san_demo">Demo</a>
 
 
 ## Model description
@@ -19,8 +18,6 @@ Our approach is fast, accurate, and only adds a few additional trainable paramet
 ![](arch.png)
 
 
-[Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://arxiv.org/abs/2302.12242)
-Mengde Xu, Zheng Zhang, Fangyun Wei, Han Hu, Xiang Bai, CVPR 2023
 
 ## Citation