Viet-Anh on Software Logo

What is: Discriminative Regularization?

SourceDiscriminative Regularization for Generative Models
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Discriminative Regularization is a regularization technique for variational autoencoders that uses representations from discriminative classifiers to augment the VAE objective function (the lower bound) corresponding to a generative model. Specifically, it encourages the model’s reconstructions to be close to the data example in a representation space defined by the hidden layers of highly-discriminative, neural network based classifiers.