HTC Seminar #24 - Self-Supervised Learning in Computer Vision
Today's HTC seminar is the week 10 guest lecture at the NYU Deep Learning 2020 course. The talk is titled "Self-supervised learning (SSL) in computer vision (CV)", and is presented by Ishan Misra of Facebook FAIR. Ishan talks about self-supervised learning (a hot topic in deep learning research currently). He dives into how 'pretext tasks' can help make SSL work, and tries to give an intuition for their underlying representations in the SSL deep learning models.
The second half of the talk forces on the shortcomings of 'pretext tasks', what their desired performance would be, and how to use Clustering and/or Contrastive Learning to get there. A specific kind of Contrastive Learning called PIRL is detailed.
I had briefly glanced at some of the papers associated with this work before, and hearing Ishra explain it really helped me understand what they were doing much better.
The link of this stuff with current data augmentation practices is very interesting. And probably suggests new things to add to the typical data augmentation ritual to get better performance.
And of course Jeremy Howard of fastai has some interesting things to say about this topic as well.