Disentangled Representation Learning Using (β-)VAE and GAN
Not on the map. Why?
Abstract (arXiv)
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 space vector of the VAE was the task of interest in this paper. The dSprite dataset provided the desired features for the required experiments in this research. After training the VAE combined with 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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 14 references that are in the map. First posted on arXiv 9 Aug 2022.
Builds on
11 of 14 references.
References · 11
- 2022Generative Adversarial Networkscited by 5,603
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
- 2018Disentangling by Factorisingcited by 614
- 2018Understanding disentangling in β-VAEcited by 332
- 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
- 2015Deep Convolutional Inverse Graphics Networkcited by 121
- 2020Old Photo Restoration via Deep Latent Space Translationcited by 27
- 2020High-Fidelity Synthesis with Disentangled Representationcited by 23
- 2021Demystifying Inductive Biases for β-VAE Based Architecturescited by 5
- 2018β-VAEs can retain label information even at high compressioncited by 2
Built on by
Not cited yet.