#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.
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
Mentioned in 1 episodes
Mentioned by 

when discussing self-supervised contrastive learning papers.


Tim Scarfe

21 snips
#55 Self-Supervised Vision Models (Dr. Ishan Misra - FAIR).