Cycle-Consistent Adversarial Learning as Approximate Bayesian Inference

Abstract

We formalize the problem of learning interdomain correspondences in the absence of paired data as Bayesian inference in a latent variable model (LVM), where one seeks the underlying hidden representations of entities from one domain as entities from the other domain. First, we introduce implicit latent variable models, where the prior over hidden representations can be specified flexibly as an implicit distribution. Next, we develop a new variational inference (VI) algorithm for this model based on minimization of the symmetric Kullback-Leibler (KL) divergence between a variational joint and the exact joint distribution. Lastly, we demonstrate that the state-of-the-art cycle-consistent adversarial learning (CYCLEGAN) models can be derived as a special case within our proposed VI framework, thus establishing its connection to approximate Bayesian inference methods.

arXiv commentPresented at the ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models. Stockholm, Sweden, 2018

References in corpus (18)

• Auto-Encoding Variational Bayes
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• Adversarial Feature Learning
• Estimating divergence functionals and the likelihood ratio by convex risk minimization
• Adversarially Learned Inference
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• Unsupervised Image-to-Image Translation Networks
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• Adversarial Autoencoders
• Learning in Implicit Generative Models
• Amortised MAP Inference for Image Super-resolution
• Least Squares Generative Adversarial Networks
• Hierarchical Implicit Models and Likelihood-Free Variational Inference
• On Unifying Deep Generative Models
• Variational Inference using Implicit Distributions
• Dropout as a Bayesian Approximation: Appendix
• Generative Adversarial Nets from a Density Ratio Estimation Perspective
• Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions

Cited by in corpus (3)

• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers
• Cross-Task Consistency Learning Framework for Multi-Task Learning