Semantic Segmentation Annotation Case Study

What is semantic segmentation?
Semantic segmentation is a computer vision task that involves assigning a semantic label to every pixel in an image. It is a form of dense prediction, where the goal is to classify each and every pixel in the input image, as opposed to object detection, where the goal is to identify and classify individual objects in the image. The semantic labels can correspond to object categories, such as “person” or “car”, or to scene elements, such as “sky” or “road”.