Update README.md

README.md

@@ -1,24 +1,12 @@
-# Contents
-
-- [Contents](#contents)
-  - [Focus-DETR Description](#focus-detr-description)
-  - [Model architecture](#model-architecture)
-  - [Dataset](#dataset)
-  - [Environment Requirements](#environment-requirements)
-  - [Eval process](#eval-process)
-    - [Usage](#usage)
-    - [Launch](#launch)
-    - [Result](#result)
-  - [ModelZoo Homepage](#modelzoo-homepage)
-
-## [Focus-DETR Description](#contents)
+# [Focus-DETR](#contents)
 
 Focus-DETR is a model that focuses attention on more informative tokens for a better trade-off between computation efficiency and model accuracy. Compared with the state-of-the-art sparse transformed-based detector under the same setting,
 our Focus-DETR gets comparable complexity while achieving 50.4AP (+2.2) on COCO.
 
 > [Paper](https://openreview.net/pdf?id=iuW96ssPQX): Less is More: Focus Attention for Efficient DETR.
 > Dehua Zheng*,  Wenhui Dong*, Hailin Hu, Xinghao Chen, Yunhe Wang.
 
+
 ## [Model architecture](#contents)
 
 Our Focus-DETR comprises a backbone network, a Transformer encoder, and a Transformer decoder. We design a foreground token selector (FTS) based on top-down score modulations across multi-scale features. And the selected tokens by a multi-category score predictor and foreground tokens go through the Pyramid Encoder to remedy the limitation of deformable attention in distant information mixing.