Indiana University Bloomington

Luddy School of Informatics, Computing, and Engineering

Technical Report TR746:
Disentangled Representation Learning Using (β-)VAE and GAN

Mohammad Haghir Ebrahimabadi
(Aug 1973), 21 - (23 including CV at the end) pages
[Master's thesis]
Given a dataset of images containing different objects with different features such as shape, size, rotation, and x-y position, and a Variational Autoencoder (VAE), creating a disentangled encoding of these features in the hidden vector space of the VAE was the task of interest in this thesis. The dSprite dataset provided the desired features for the required experiments in this research. After training the VAE with combinations of a Generative Adversarial Network (GAN), each dimension of the hidden vector was disrupted to explore the disentanglement in each dimension. Note that the GAN was used to improve the quality of output image reconstruction.

Available as: