Deep Generative Models

A theory of independent mechanisms for extrapolation in generative models
Generative models can be trained to emulate complex empirical data, but are they useful to make predictions in the context of …
Michel Besserve, Remy Sun, Dominik Janzing, Bernhard Schölkopf
PDF Cite
A theory of independent mechanisms for extrapolation in generative models
Counterfactuals uncover the modular structure of deep generative models
Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data. …
Michel Besserve, Arash Mehrjou, Remy Sun, Bernhard Schölkopf
PDF Cite
Counterfactuals uncover the modular structure of deep generative models
Exploiting the modularity of deep networks to generate visual counterfactuals
Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data. …
Michel Besserve, Arash Mehrjou, Remy Sun, Bernhard Schölkopf
PDF Cite
Intrinsic disentanglement an invariance view for deep generative models
Deep generative models such as Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs) are important tools to …
Michel Besserve, Remy Sun, Bernhard Schölkopf
PDF Cite Poster Video Source Document