diff --git a/docs/note/source_en/model_lite.rst b/docs/note/source_en/model_lite.rst
index bb6b04ac6fed42dbe42d78fe55d329edd5e5d0b8..2fa38b248c3a167289094cfe865936cef089d0e6 100644
--- a/docs/note/source_en/model_lite.rst
+++ b/docs/note/source_en/model_lite.rst
@@ -8,4 +8,5 @@
   object_detection_lite
   posenet_lite
   image_segmentation_lite
-  style_transfer_lite
\ No newline at end of file
+  style_transfer_lite
+  scene_detection_lite
\ No newline at end of file
diff --git a/docs/note/source_en/object_detection_lite.md b/docs/note/source_en/object_detection_lite.md
index 4d571b5955c3c6a8d0abd050602c715590b17ec0..a0c07e24a717322c025f91eb42be30e57511a6b1 100644
--- a/docs/note/source_en/object_detection_lite.md
+++ b/docs/note/source_en/object_detection_lite.md
@@ -20,7 +20,7 @@ The following table shows the data of some object detection models using MindSpo
 
 > The performance of the table below is tested on the mate30.
 
-| Model name      | Size | mAP(IoU=0.50:0.95) | CPU 4 thread delay (ms) |
+| Model name      | Size(Mb)  | mAP(IoU=0.50:0.95) | CPU 4 thread delay (ms) |
 |-----------------------| :----------: | :----------: | :-----------: |
 | [MobileNetv2-SSD](https://download.mindspore.cn/model_zoo/official/lite/ssd_mobilenetv2_lite/ssd.ms) | 16.7 | 0.22 | 25.4 |
 | [GhostNet-SSD](https://download.mindspore.cn/model_zoo/official/lite/ssd_ghostnet_lite/ssd.ms) | 25.7 | 0.24 | 24.1 |
diff --git a/docs/note/source_en/scene_detection_lite.md b/docs/note/source_en/scene_detection_lite.md
new file mode 100644
index 0000000000000000000000000000000000000000..0bd910475c637ea7b6380ce984670df44eb56aeb
--- /dev/null
+++ b/docs/note/source_en/scene_detection_lite.md
@@ -0,0 +1,19 @@
+# Scene Detection Model Support (Lite)
+
+<a href="https://gitee.com/mindspore/docs/blob/master/docs/note/source_en/scene_detection_lite.md" target="_blank"><img src="./_static/logo_source.png"></a>
+
+## Scene dectectin introduction
+
+Scene detection can identify the type of scene in the device's camera.
+
+Using MindSpore Lite to implement scene detection [example](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/lite/scene_detection).
+
+## Scene detection model list
+
+The following table shows the data of some scene detection models using MindSpore Lite inference.
+
+> The performance of the table below is tested on the P30.
+
+| Model name              | Size(Mb)  | Top1 | CPU 4 thread delay (ms) |
+|-----------------------| :----------: | :----------: | :-----------: |
+| [MobileNetv2](https://download.mindspore.cn/model_zoo/official/lite/mobilenetv2_openimage_lite/mobilenetv2.ms) | 11.3 | - | 11.5 |
diff --git a/docs/note/source_zh_cn/model_lite.rst b/docs/note/source_zh_cn/model_lite.rst
index 3a0b8a844a89202f825062eb769e7a026da2663a..f2be842d93debe0d5174bfd3498f953c8d2f0904 100644
--- a/docs/note/source_zh_cn/model_lite.rst
+++ b/docs/note/source_zh_cn/model_lite.rst
@@ -8,4 +8,5 @@
   object_detection_lite
   posenet_lite
   image_segmentation_lite
-  style_transfer_lite
\ No newline at end of file
+  style_transfer_lite
+  scene_detection_lite
\ No newline at end of file
diff --git a/docs/note/source_zh_cn/object_detection_lite.md b/docs/note/source_zh_cn/object_detection_lite.md
index a39c84593fdde248d44326b71e9b0d894938ba78..df8116ba720dfead4d51136bda50a4dd9236134a 100644
--- a/docs/note/source_zh_cn/object_detection_lite.md
+++ b/docs/note/source_zh_cn/object_detection_lite.md
@@ -20,7 +20,7 @@
 
 > 下表的性能是在mate30手机上测试的。
 
-| 模型名称               | 大小 | mAP(IoU=0.50:0.95) | CPU 4线程时延(ms) |
+| 模型名称               | 大小(Mb)  | mAP(IoU=0.50:0.95) | CPU 4线程时延(ms) |
 |-----------------------| :----------: | :----------: | :-----------: |
 | [MobileNetv2-SSD](https://download.mindspore.cn/model_zoo/official/lite/ssd_mobilenetv2_lite/ssd.ms) | 16.7 | 0.22 | 25.4 |
 | [GhostNet-SSD](https://download.mindspore.cn/model_zoo/official/lite/ssd_ghostnet_lite/ssd.ms) | 25.7 | 0.24 | 24.1 |
diff --git a/docs/note/source_zh_cn/scene_detection_lite.md b/docs/note/source_zh_cn/scene_detection_lite.md
new file mode 100644
index 0000000000000000000000000000000000000000..19b3d7db410944cf9a4d1e14e10ed4a5c828cf76
--- /dev/null
+++ b/docs/note/source_zh_cn/scene_detection_lite.md
@@ -0,0 +1,19 @@
+# 场景检测模型支持（Lite）
+
+<a href="https://gitee.com/mindspore/docs/blob/master/docs/note/source_zh_cn/scene_detection_lite.md" target="_blank"><img src="./_static/logo_source.png"></a>
+
+## 场景检测介绍
+
+场景检测可以识别设备摄像头中场景的类型。
+
+使用MindSpore Lite实现场景检测的[示例代码](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/lite/scene_detection)。
+
+## 场景检测模型列表
+
+下表是使用MindSpore Lite推理的部分场景检测模型的数据。
+
+> 下表的性能是在P30手机上测试的。
+
+| 模型名称               | 大小(Mb) | Top1 | CPU 4线程时延(ms) |
+|-----------------------| :----------: | :----------: | :-----------: |
+| [MobileNetv2](https://download.mindspore.cn/model_zoo/official/lite/mobilenetv2_openimage_lite/mobilenetv2.ms) | 11.3 | - | 11.5 |