Weighted Loss Functions for Instance Segmentation
This post is a follow up to my talk, Practical Image Classification & Object Detection at PyData Delhi 2018. You can watch the talk here:
and see the slides here.
I spoke at length about the different kinds of problems in computer vision and how they are interpreted in deep learning architectures. I spent a fair bit of time on instance and semantic segmentation (for an introduction to these problems, watch Justin Johnson’s lecture from the Stanford CS231 course here). In short, semantic segmentation deals with designating each pixel of an image as belonging to a class, and instance segmentation deals with identifying which instance of a class each pixel belongs to. The following images show an example of semantic versus instance segmentation.