Jim Portegies — accepted AI-conference papers

2022

Quantifying and Learning Linear Symmetry-Based Disentanglement

Loek Tonnaer, Luis Armando Perez Rey, Vlado Menkovski, Mike Holenderski, Jim Portegies

ICML 2022spotlight

The definition of Linear Symmetry-Based Disentanglement (LSBD) formalizes the notion of linearly disentangled representations, but there is currently no metric to quantify LSBD. Such a metric is crucial to evaluate LSBD methods and to compare them to previous understandings of disentanglement. We pr…

Cited by 22 Source ↗PDF ↗code ↗Scholar ↗

2020

Diffusion Variational Autoencoders

Luis A. Perez Rey, Vlado Menkovski, Jim Portegies

IJCAI 2020poster

A standard Variational Autoencoder, with a Euclidean latent space, is structurally incapable of capturing topological properties of certain datasets. To remove topological obstructions, we introduce Diffusion Variational Autoencoders (DeltaVAE) with arbitrary (closed) manifolds as a latent space. A…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗