Issam Laradji is currently a Postdoc at McGill and an intern at ElementAI, a ServiceNow company. He is interested at developing methods that require weaker supervision in order to reduce the amount of effort humans need for acquiring training sets. His current focus is on 3D computer vision that touch on rendering, synthesizing novel scenes, and learning to infer physical properties of objects. On the side, he occasionally works on new optimization methods for deep learning. He also continuously works on and maintains Haven-AI (https://github.com/haven-ai/haven-ai) which is a library for running, managing and visualizing large scale experiments in the hopes to make machine learning research accessible and reproducible to people.
Week 8 Closing Ceremony Speaker: A Weakly Supervised Consistency-based Learning Method for COVID-19 Segmentation in CT Images
In this presentation I will discuss one of our works on COVID-19 Segmentation in CT Images. It will include a brief description of the motivation for using a weakly supervised method for this task, and a description on how this method leverages a consistency-based learning approach to achieve better segmentation results. I will also include a tutorial for running the code and getting results which could help for setting up a codebase or a benchmark for the Hackathon.