#45861
Mentioned in 1 episodes

Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples

PAWS Method
Book • 2021
This paper introduces PAWS, a method for semi-supervised learning that combines labeled and unlabeled data to train models efficiently.

PAWS minimizes a consistency loss to ensure similar pseudo-labels for different views of the same image, leveraging labeled samples non-parametrically.

It achieves state-of-the-art results on ImageNet with significantly less training time.

Mentioned by

undefined
Tim Scarfe

Mentioned in 1 episodes

Mentioned by
undefined
Tim Scarfe
when discussing self-supervised contrastive learning papers.
21 snips
#55 Self-Supervised Vision Models (Dr. Ishan Misra - FAIR).

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app