Video není dostupné.
Omlouváme se.
Semi-Weak Supervised Learning
Vložit
- čas přidán 18. 08. 2024
- Research Paper: arxiv.org/pdf/...
Blog Post: / billion-scale-semi-sup...
Github Repository: github.com/fac...
Facebook has recently presented a really interesting framework to make use of 1 billion weakly-supervised Instagram images (labeled with hashtags) using a model-distillation pipeline. Thanks for watching, please subscribe!
This paper is on my to-read list and now I'll understand what I'm getting into a whole lot more easily. Thanks for the great video!
Thank you so much! I really hope you find the paper interesting, I was surprised at the relative lack of interest following their first paper on weak supervision with instagram pictures!
@@connor-shorten I haven't read that either, guess that's going on the never ending list as well lol
Henry! Thank you!!! 👏👏👏👏👏👏👏👏👏👏👏👏
Really hope you like this video! I thought the consideration of class imbalance for weakly supervised dataset and the need for inference accelerators for large scale model distillation were really interesting!
Small Correction: The intro conflates semi-supervision and weak-supervision
Thank you so much! Great review.
Thank you!!
God bless, this was a great video.
So what would be the point if you already have a model that does well in the first place, there is no need for the student model
The student model gets much more better at classification, the student model runs from both teacher(itself, or a large capacity model) and labelled dataset.