A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
[article]
2022
arXiv
pre-print
Self-supervised representation learning has shown remarkable success in a number of domains. A common practice is to perform data augmentation via hand-crafted transformations intended to leave the semantics of the data invariant. We seek to understand the empirical success of this approach from a theoretical perspective. We formulate the augmentation process as a latent variable model by postulating a partition of the latent representation into a content component, which is assumed invariant
arXiv:2106.04619v4
fatcat:hv7lcnafzregngqaks2rrbfxpm