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...
Príomhchruthaitheoirí: | Mathieu, E, Rainforth, T, Siddharth, N, Teh, Y |
---|---|
Formáid: | Conference item |
Foilsithe / Cruthaithe: |
PMLR
2019
|
Míreanna comhchosúla
-
AD-VAE: Adversarial Disentangling Variational Autoencoder
de réir: Adson Silva, et al.
Foilsithe / Cruthaithe: (2025-03-01) -
Disentangled Sequential Variational Autoencoder for Collaborative Filtering
de réir: WU Mei-lin, HUANG Jia-jin, QIN Jin
Foilsithe / Cruthaithe: (2022-12-01) -
Sequential Variational Autoencoder with Adversarial Classifier for Video Disentanglement
de réir: Takeshi Haga, et al.
Foilsithe / Cruthaithe: (2023-02-01) -
Disentangling Generative Factors of Physical Fields Using Variational Autoencoders
de réir: Christian Jacobsen, et al.
Foilsithe / Cruthaithe: (2022-06-01) -
On the fairness of disentangled representations
de réir: Locatello, F, et al.
Foilsithe / Cruthaithe: (2019)