diff --git a/PaddleMono/README.md b/PaddleMono/README.md
index bdf21ac..9181cb8 100644
--- a/PaddleMono/README.md
+++ b/PaddleMono/README.md
@@ -27,7 +27,7 @@ As initial version, we support the following algoirthms. We are working on more
 1. [Monodepth2 (ICCV2019)[1]](configs/monodepthv2/README.md)
 2. [MLDA-Net (TIP2021)[2]](configs/mldanet/README.md)
 3. [Depth Hints (ICCV2019)[3]](configs/depth_hints/README.md)
-4. [BTS[4]](configs/bts/README.md)
+4. [BTS[4]](configs/BTS/README.md)
 
 Please click the hyperlink of each algorithm for more detailed explanation.
 
diff --git a/PaddleMono/README_zh-CN.md b/PaddleMono/README_zh-CN.md
index ce7536a..9c75912 100644
--- a/PaddleMono/README_zh-CN.md
+++ b/PaddleMono/README_zh-CN.md
@@ -25,7 +25,7 @@ PaddleMono是一款基于 PaddlePaddle 的单目深度估计工具箱，是 Padd
 1. [Monodepth2 (ICCV2019)[1]](configs/monodepthv2/README.md)
 2. [MLDA-Net (TIP2021)[2]](configs/mldanet/README.md)
 3. [Depth Hints (ICCV2019)[3]](configs/depth_hints/README.md)
-4. [BTS[4]](configs/bts/README.md)
+4. [BTS[4]](configs/BTS/README.md)
 
 请点击上方的超链接查看每个算法的实现细节
 
diff --git a/PaddleMono/configs/BTS/README.md b/PaddleMono/configs/BTS/README.md
index 4d4faa5..cfb495e 100644
--- a/PaddleMono/configs/BTS/README.md
+++ b/PaddleMono/configs/BTS/README.md
@@ -1,14 +1,10 @@
 # BTS
-A paddle implementation of the paper From big to small: Multi-scale local planar guidance for monocular depth estimation
-[\[arXiv: Computer Vision and Pattern Recognition\]](https://arxiv.org/abs/1907.10326v5)
+A paddle implementation of the paper [From big to small: Multi-scale local planar guidance for monocular depth estimation](https://arxiv.org/abs/1907.10326v5)
 
 
 ## Abstract
 A supervised monocular depth estimation network. BTS propose a network architecture that utilizes novel local planar guidance layers located at multiple stages in the decoding phase.
 
-## Training
-The code for ***BTS*** builds upon [BTS](configs/BTS/README.md).
-
 [comment]: <> (<!-- **KITTI Datasets Pretraining**)
 
 [comment]: <> (Run the script `./configs/bts/bts.sh` to pre-train on KITTI datsets. Please update `--data_path` in the bash file as your training data path.)