Discriminative Regularization

2000년 도입 · 논문 6편에서 사용

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.

출처: Discriminative Regularization for Generative Models

소개 논문: Discriminative Regularization for Generative Models