Introspective Generative Modeling: Decide Discriminatively

04/25/2017
by   Justin Lazarow, et al.
0

We study unsupervised learning by developing introspective generative modeling (IGM) that attains a generator using progressively learned deep convolutional neural networks. The generator is itself a discriminator, capable of introspection: being able to self-evaluate the difference between its generated samples and the given training data. When followed by repeated discriminative learning, desirable properties of modern discriminative classifiers are directly inherited by the generator. IGM learns a cascade of CNN classifiers using a synthesis-by-classification algorithm. In the experiments, we observe encouraging results on a number of applications including texture modeling, artistic style transferring, face modeling, and semi-supervised learning.

READ FULL TEXT

page 1

page 4

page 7

page 8

research
11/24/2017

Wasserstein Introspective Neural Networks

We present Wasserstein introspective neural networks (WINN) that are bot...
research
11/19/2016

Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks

We introduce a simple semi-supervised learning approach for images based...
research
03/28/2014

Data generator based on RBF network

There are plenty of problems where the data available is scarce and expe...
research
04/25/2017

Introspective Classifier Learning: Empower Generatively

In this paper we propose introspective classifier learning (ICL) that em...
research
10/27/2022

Articulation GAN: Unsupervised modeling of articulatory learning

Generative deep neural networks are widely used for speech synthesis, bu...
research
11/21/2018

Self-Adversarially Learned Bayesian Sampling

Scalable Bayesian sampling is playing an important role in modern machin...

Please sign up or login with your details

Forgot password? Click here to reset