Experiments for understanding disentanglement in VAE latent representations

Pytorch implementation of β-VAE

Dataset to assess the disentanglement properties of unsupervised learning methods

Pytorch implementation of FactorVAE proposed in Disentangling by Factorising(http://arxiv.org/abs/1802.05983)

Replicating "Understanding disentangling in β-VAE"

Deep active inference agents using Monte-Carlo methods

[ICML 2020] InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs

This is the code for the paper Embrace the Gap: VAEs perform Independent Mechanism Analysis, showing that optimizing the ELBO is equivalent to optimizing the IMA-regularized log-likelihood under certain assumptions (e.g., small decoder variance).

A TensorFlow implementation of FactorVAE, proposed in "Disentangling by Factorising" by Kim et al.

ML2 Project following ControlVAE: Tuning, Analytical Properties, and Performance Analysis

Generation of sprite dataset used when testing disentangled models.