Updated PointRend

Author: kapil-varshney

guide/14-deep-learning/How_MaskRCNN_works.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## How MaskRCNN Works?"
+    "## How Mask R-CNN Works?"
    ]
   },
   {
@@ -119,9 +119,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### PointRend Enhancement\n",
-    "\n",
-    "Segmentation models can tend to over-smoothen boundaries which might not be precise for objects or scenes with irregular boundaries. To get a crisp segmentation boundary, a point-based rendering neural network module called [**PointRend**](https://arxiv.org/abs/1912.08193) has been added as an enhancement to the existing model. This module draws methodology from classical computer graphics and gives the perspective of rendering to a segmentation problem. Image segmentation models often predict labels on a low-resolution regular grid, for example, 1/8th of the input. These models use interpolation to upscale the predictions to original resolution. In contrast, PointRend uses iterative subdivision algorithm to upscale the predictions by predicting labels of points at selected locations by a trained small neural network. This method enables high-resolution output in an efficient way. [3]"
+    "### PointRend Enhancement"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Segmentation models can tend to generate over-smooth boundaries which might not be precise for objects or scenes with irregular boundaries. To get a crisp segmentation boundary, a point-based rendering neural network module called [**PointRend**](https://arxiv.org/abs/1912.08193) has been added as an enhancement to the existing model. This module draws methodology from classical computer graphics and gives the perspective of rendering to a segmentation problem. Image segmentation models often predict labels on a low-resolution regular grid, for example, 1/8th of the input. These models use interpolation to upscale the predictions to original resolution. In contrast, PointRend uses iterative subdivision algorithm to upscale the predictions by predicting labels of points at selected locations by a trained small neural network. This method enables high-resolution output in an efficient way. [3]"
    ]
   },
   {

guide/14-deep-learning/how_deeplabv3_works.ipynb

@@ -159,9 +159,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### PointRend Enhancement\n",
-    "\n",
-    "Segmentation models can tend to over-smoothen boundaries which might not be precise for objects or scenes with irregular boundaries. To get a crisp segmentation boundary, a point-based rendering neural network module called [**PointRend**](https://arxiv.org/abs/1912.08193) has been added as an enhancement to the existing model. This module draws methodology from classical computer graphics and gives the perspective of rendering to a segmentation problem. Image segmentation models often predict labels on a low-resolution regular grid, for example, 1/8th of the input. These models use interpolation to upscale the predictions to original resolution. In contrast, PointRend uses iterative subdivision algorithm to upscale the predictions by predicting labels of points at selected locations by a trained small neural network. This method enables high-resolution output in an efficient way. [8]"
+    "### PointRend Enhancement"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Segmentation models can tend to generate over-smooth boundaries which might not be precise for objects or scenes with irregular boundaries. To get a crisp segmentation boundary, a point-based rendering neural network module called [**PointRend**](https://arxiv.org/abs/1912.08193) has been added as an enhancement to the existing model. This module draws methodology from classical computer graphics and gives the perspective of rendering to a segmentation problem. Image segmentation models often predict labels on a low-resolution regular grid, for example, 1/8th of the input. These models use interpolation to upscale the predictions to original resolution. In contrast, PointRend uses iterative subdivision algorithm to upscale the predictions by predicting labels of points at selected locations by a trained small neural network. This method enables high-resolution output in an efficient way. [8]"
    ]
   },
   {

guide/14-deep-learning/how_pspnet_works.ipynb

@@ -277,9 +277,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### PointRend Enhancement\n",
-    "\n",
-    "Segmentation models can tend to over-smoothen boundaries which might not be precise for objects or scenes with irregular boundaries. To get a crisp segmentation boundary, a point-based rendering neural network module called [**PointRend**](https://arxiv.org/abs/1912.08193) has been added as an enhancement to the existing model. This module draws methodology from classical computer graphics and gives the perspective of rendering to a segmentation problem. Image segmentation models often predict labels on a low-resolution regular grid, for example, 1/8th of the input. These models use interpolation to upscale the predictions to original resolution. In contrast, PointRend uses iterative subdivision algorithm to upscale the predictions by predicting labels of points at selected locations by a trained small neural network. This method enables high-resolution output in an efficient way. [9]"
+    "### PointRend Enhancement"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Segmentation models can tend to generate over-smooth boundaries which might not be precise for objects or scenes with irregular boundaries. To get a crisp segmentation boundary, a point-based rendering neural network module called [**PointRend**](https://arxiv.org/abs/1912.08193) has been added as an enhancement to the existing model. This module draws methodology from classical computer graphics and gives the perspective of rendering to a segmentation problem. Image segmentation models often predict labels on a low-resolution regular grid, for example, 1/8th of the input. These models use interpolation to upscale the predictions to original resolution. In contrast, PointRend uses iterative subdivision algorithm to upscale the predictions by predicting labels of points at selected locations by a trained small neural network. This method enables high-resolution output in an efficient way. [9]"
    ]
   },
   {