Adversarial Fisher Vectors for Unsupervised Representation Learning

Walter Talbott
Walter Talbott
Joshua M. Susskind
Joshua M. Susskind

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019.

Cited by: 0|Bibtex|Views21

Abstract:

We examine Generative Adversarial Networks (GANs) through the lens of deep Energy Based Models (EBMs), with the goal of exploiting the density model that follows from this formulation. In contrast to a traditional view where the discriminator learns a constant function when reaching convergence, here we show that it can provide useful inf...More

Code:

Data:

Your rating :
0

 

Tags
Comments