News for hackers. Stuff that matters.

A comment on Illustrated FixMatch for semi-supervised learning.

Re:Illustrated FixMatch for semi-supervised learning by jonpon on Friday April 03, 2020 @01:28PM (#22771845)
Great summary! Reminds me a lot about Leon Bottou's work on using deep learning to learn causal invariant representations. (Video: https://www.youtube.com/watch?v=lbZNQt0Q5HA)

We can view the augmentations of the image as "interventions" forcing the model to learn an invariant representation of the image.

Although the blog post did not frame it as this type of problem (not sure if the paper did), I think it can definitely be seen as such and is really promising.

[ Parent | on HN ]
Re:Illustrated FixMatch for semi-supervised learning by amitness on Friday April 03, 2020 @01:34PM (#22771940)
Interesting, thank you for sharing that. It reminds me of this approach called "PIRL" by Facebook AI. They framed the problem to learn invariant representations. You might find it interesting.

https://amitness.com/2020/03/illustrated-pirl/

[ Parent | on HN ]