Disentangling disentanglement in variational autoencoders
We develop a generalisation of disentanglement in variational autoencoders (VAEs)—decomposition of the latent representation—characterising it as the fulfilment of two factors: a) the latent encodings of the data having an appropriate level of overlap, and b) the aggregate encoding of the data confo...
Κύριοι συγγραφείς: | Mathieu, E, Rainforth, T, Siddharth, N, Teh, Y |
---|---|
Μορφή: | Conference item |
Έκδοση: |
PMLR
2019
|
Παρόμοια τεκμήρια
Παρόμοια τεκμήρια
-
AD-VAE: Adversarial Disentangling Variational Autoencoder
ανά: Adson Silva, κ.ά.
Έκδοση: (2025-03-01) -
Disentangled Sequential Variational Autoencoder for Collaborative Filtering
ανά: WU Mei-lin, HUANG Jia-jin, QIN Jin
Έκδοση: (2022-12-01) -
Sequential Variational Autoencoder with Adversarial Classifier for Video Disentanglement
ανά: Takeshi Haga, κ.ά.
Έκδοση: (2023-02-01) -
Disentangling Generative Factors of Physical Fields Using Variational Autoencoders
ανά: Christian Jacobsen, κ.ά.
Έκδοση: (2022-06-01) -
On the fairness of disentangled representations
ανά: Locatello, F, κ.ά.
Έκδοση: (2019)