ISA-VAE: Independent Subspace Analysis with Variational Autoencoders

By Jan Stühmer, Richard E. Turner, Sebastian Nowozin. 2018

5 citations recorded by the source corpus.

Citations in the corpus

• On the Fairness of Disentangled Representations (2019, neutral): “ntations cannot be identified. However, existing methods heavily rely on inductive biases such as architecture, hyperparameter choices, mean-field assumptions, and smoothness induced through randomness [65, 80, 86]. In practice, training a large number of models with different losses and hyperparamete”