# Set Distribution Networks: a Generative Model for Sets of Images

Walter Talbott
Miguel Angel Bautista
Josh M. Susskind
Cited by: 0|Bibtex|Views68

Abstract:

Images with shared characteristics naturally form sets. For example, in a face verification benchmark, images of the same identity form sets. For generative models, the standard way of dealing with sets is to represent each as a one hot vector, and learn a conditional generative model $p(\mathbf{x}|\mathbf{y})$. This representation assu...More

Code:

Data:

0

Tags