Journal article icon

Journal article

Improving generative modelling in VAEs using Multimodal Prior

Abstract:
In this paper we propose a conditional generative modelling (CGM) approach for unsupervised disentangled representation learning using variational autoencoder (VAE). CGM employs a multimodal/categorical conditional prior distribution in the latent space to learn global uncertainty in data by modelling the variations at local level. Thus, the proposed framework enforces the model to independently estimate the inherent patterns within each category, which improves the interpretability of the latent representations learned by the VAE model. The evidence lower bound objective for training the generative model is maximized using a mutual information criterion between the global latent categorical variable and the encoded inputs. Further, the approach has a built-in mechanism for bounding the information flow between the encoder and the decoder which addresses the problems of posterior collapse in conventional VAE models. Experiments on a variety of datasets demonstrate that our objective can learn disentangled representations and the proposed approach achieves competitive results on various task such as generative modelling, image classification and image denoising.
Publication status:
Accepted
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1109/TMM.2020.3008053

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Mathematical Institute
Sub department:
Mathematical Institute
Role:
Author
ORCID:
0000-0001-8149-8151
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Sub department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Sub department:
Engineering Science
Role:
Author


Publisher:
Institute of Electrical and Electronics Engineers
Journal:
IEEE Transactions on Multimedia More from this journal
Volume:
23
Pages:
2153 - 2161
Publication date:
2020-07-08
Acceptance date:
2020-06-23
DOI:
EISSN:
1941-0077
ISSN:
1520-9210


Language:
English
Keywords:
Pubs id:
1116905
Local pid:
pubs:1116905
Deposit date:
2020-07-17
ARK identifier:

Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP