diff --git a/README.md b/README.md
index 0e58a9e5db946b3142a2b81d131241c8ed379231..981f0a76385de68229faedae110567ea0ecaec48 100644
--- a/README.md
+++ b/README.md
@@ -6,6 +6,9 @@
 
 PaddleClas is a toolset for image classification tasks prepared for the industry and academia. It helps users train better computer vision models and apply them in real scenarios.
 
+
+**Note**: Baidu proposed a new image classification network structure **`HS-ResNet`**, which reaches 81.3% on ImageNet-1k dataset, while its `params` is almost same as `ResNet50`.The arxiv link is here: [HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network](https://arxiv.org/pdf/2010.07621.pdf). The model structure and the pretrained weights are coming soon!
+
 **Recent update**
 - 2020.09.17 Add `Res2Net50_vd_26w_4s_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 83.1%. Add `Res2Net101_vd_26w_4s_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 83.9%.
 - 2020.10.12 Add Paddle-Lite demo。
diff --git a/README_cn.md b/README_cn.md
index 7329a5a073e32adf39168a3c1b90ca80a2699a79..d3a76e63711ff1fc10175302ec2506245cb5e873 100644
--- a/README_cn.md
+++ b/README_cn.md
@@ -6,6 +6,9 @@
 
 飞桨图像分类套件PaddleClas是飞桨为工业界和学术界所准备的一个图像分类任务的工具集，助力使用者训练出更好的视觉模型和应用落地。
 
+
+**注意**: 百度提出了一个新的图像分类网络结构**`HS-ResNet`**，基于ImageNet-1k数据集，`HS-ResNet`在与`ResNet`的params相近的情况下，Top-1 Acc达到了81.3%，相应的Arxiv文章链接可以参考这里：[HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network](https://arxiv.org/pdf/2010.07621.pdf)，模型结构和预训练模型参数即将开源，敬请期待！
+
 **近期更新**
 - 2020.10.20 添加 `Res2Net50_vd_26w_4s_ssld `模型，在ImageNet-1k上Top-1 Acc可达83.1%；添加 `Res2Net101_vd_26w_4s_ssld `模型，在ImageNet-1k上Top-1 Acc可达83.9%。
 - 2020.10.12 添加Paddle-Lite demo。
diff --git a/docs/images/models/T4_benchmark/t4.fp32.bs4.main_fps_top1.png b/docs/images/models/T4_benchmark/t4.fp32.bs4.main_fps_top1.png
index a6b783c58066045bb5ce5e814f2afe5d1c846380..a9165bdd9816451785e05c37e243cd4be2253bc3 100644
Binary files a/docs/images/models/T4_benchmark/t4.fp32.bs4.main_fps_top1.png and b/docs/images/models/T4_benchmark/t4.fp32.bs4.main_fps_top1.png differ