update readme

README.md

@@ -1,11 +1,8 @@
+[![NVIDIA Source Code License](https://img.shields.io/badge/license-NSCL-blue.svg)](https://github.com/NVlabs/SegFormer/blob/master/LICENSE)
+![Python 3.7](https://img.shields.io/badge/python-3.7-green.svg)
+
 # SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
 
-This repository contains PyTorch evaluation code, training code and pretrained models for [SegFormer](https://arxiv.org/abs/2105.15203).
-
-SegFormer is a simple, efficient and powerful semantic segmentation method, as shown in Figure 1.
-
-We use [MMSegmentation v0.13.0](https://github.com/open-mmlab/mmsegmentation/tree/v0.13.0) as the codebase.
-
 <!-- ![image](resources/image.png) -->
 <div align="center">
   <img src="./resources/image.png" height="400">
@@ -14,9 +11,19 @@ We use [MMSegmentation v0.13.0](https://github.com/open-mmlab/mmsegmentation/tre
   Figure 1: Performance of SegFormer-B0 to SegFormer-B5.
 </p>
 
+### [Project page](https://github.com/NVlabs/SegFormer) | [Paper](https://arxiv.org/abs/2105.15203) | [Demo (Youtube)](https://www.youtube.com/watch?v=J0MoRQzZe8U) | [Demo (Bilibili)](https://www.bilibili.com/video/BV1MV41147Ko/)
 
+SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers.<br>
+[Enze Xie](https://xieenze.github.io/), [Wenhai Wang](https://whai362.github.io/), [Zhiding Yu](https://chrisding.github.io/), [Anima Anandkumar](https://tensorlab.cms.caltech.edu/users/anima/), [Jose M. Alvarez](https://rsu.data61.csiro.au/people/jalvarez/), and [Ping Luo](http://luoping.me/).<br>
+Technical Report 2021.
 
-## Install
+This repository contains the PyTorch training/evaluation code and the pretrained models for [SegFormer](https://arxiv.org/abs/2105.15203).
+
+SegFormer is a simple, efficient and powerful semantic segmentation method, as shown in Figure 1.
+
+We use [MMSegmentation v0.13.0](https://github.com/open-mmlab/mmsegmentation/tree/v0.13.0) as the codebase.
+
+## Installation
 
 For install and data preparation, please refer to the guidelines in [MMSegmentation v0.13.0](https://github.com/open-mmlab/mmsegmentation/tree/v0.13.0).
 
@@ -30,13 +37,13 @@ Download [trained weights](https://drive.google.com/drive/folders/1GAku0G0iR9DsB
 Example: evaluate ```SegFormer-B1``` on ```ADE20K```:
 
 ```
-# single-gpu testing
+# Single-gpu testing
 python tools/test.py local_configs/segformer/B1/segformer.b1.512x512.ade.160k.py /path/to/checkpoint_file
 
-# multi-gpu testing
+# Multi-gpu testing
 ./tools/dist_test.sh local_configs/segformer/B1/segformer.b1.512x512.ade.160k.py /path/to/checkpoint_file <GPU_NUM>
 
-# multi-gpu, multi-scale testing
+# Multi-gpu, multi-scale testing
 tools/dist_test.sh local_configs/segformer/B1/segformer.b1.512x512.ade.160k.py /path/to/checkpoint_file <GPU_NUM> --aug-test
 ```
 
@@ -47,10 +54,10 @@ Download [weights](https://drive.google.com/drive/folders/1b7bwrInTW4VLEm27YawHO
 Example: train ```SegFormer-B1``` on ```ADE20K```:
 
 ```
-# single-gpu training
+# Single-gpu training
 python tools/train.py local_configs/segformer/B1/segformer.b1.512x512.ade.160k.py 
 
-# multi-gpu training
+# Multi-gpu training
 ./tools/dist_train.sh local_configs/segformer/B1/segformer.b1.512x512.ade.160k.py <GPU_NUM>
 ```
 
@@ -60,7 +67,7 @@ evaluation purposes only. For business inquiries, please contact
 [researchinquiries@nvidia.com](mailto:researchinquiries@nvidia.com).
 
 
-## Citing SegFormer
+## Citation
 ```
 @article{xie2021segformer,
   title={SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers},