Evaluating Self-Supervised Pretraining Without Using Labels

Colorado Reed
Colorado Reed
Sean Metzger
Sean Metzger
Aravind Srinivas
Aravind Srinivas
Cited by: 0|Bibtex|Views25
Other Links: arxiv.org

Abstract:

A common practice in unsupervised representation learning is to use labeled data to evaluate the learned representations - oftentimes using the labels from the "unlabeled" training dataset. This supervised evaluation is then used to guide the training process, e.g. to select augmentation policies. However, supervised evaluations may not...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments