Updated PointRend description

Author: kapil-varshney

guide/14-deep-learning/How_MaskRCNN_works.ipynb

@@ -121,7 +121,7 @@
    "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. An iterative subdivision algorithm at selected locations is used to make point-based segmentation predictions. This method enables high-resolution output in an efficient way. [3]"
+    "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]"
    ]
   },
   {
@@ -154,13 +154,6 @@
     "\n",
     "[3] Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick: “PointRend: Image Segmentation as Rendering”, 2019; [http://arxiv.org/abs/1912.08193 arXiv:1912.08193]."
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

guide/14-deep-learning/how_deeplabv3_works.ipynb

@@ -161,7 +161,7 @@
    "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. An iterative subdivision algorithm at selected locations is used to make point-based segmentation predictions. This method enables high-resolution output in an efficient way. [8]"
+    "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]"
    ]
   },
   {
@@ -214,13 +214,6 @@
     "\n",
     "[8] Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick: “PointRend: Image Segmentation as Rendering”, 2019; [http://arxiv.org/abs/1912.08193 arXiv:1912.08193].\n"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

guide/14-deep-learning/how_pspnet_works.ipynb

@@ -279,7 +279,7 @@
    "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. An iterative subdivision algorithm at selected locations is used to make point-based segmentation predictions. This method enables high-resolution output in an efficient way. [9]"
+    "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]"
    ]
   },
   {
@@ -338,13 +338,6 @@
     "\n",
     "[9] Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick: “PointRend: Image Segmentation as Rendering”, 2019; [http://arxiv.org/abs/1912.08193 arXiv:1912.08193]."
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {