DeepAI AI Chat
Log In Sign Up

dpVAEs: Fixing Sample Generation for Regularized VAEs

by   Riddhish Bhalodia, et al.

Unsupervised representation learning via generative modeling is a staple to many computer vision applications in the absence of labeled data. Variational Autoencoders (VAEs) are powerful generative models that learn representations useful for data generation. However, due to inherent challenges in the training objective, VAEs fail to learn useful representations amenable for downstream tasks. Regularization-based methods that attempt to improve the representation learning aspect of VAEs come at a price: poor sample generation. In this paper, we explore this representation-generation trade-off for regularized VAEs and introduce a new family of priors, namely decoupled priors, or dpVAEs, that decouple the representation space from the generation space. This decoupling enables the use of VAE regularizers on the representation space without impacting the distribution used for sample generation, and thereby reaping the representation learning benefits of the regularizations without sacrificing the sample generation. dpVAE leverages invertible networks to learn a bijective mapping from an arbitrarily complex representation distribution to a simple, tractable, generative distribution. Decoupled priors can be adapted to the state-of-the-art VAE regularizers without additional hyperparameter tuning. We showcase the use of dpVAEs with different regularizers. Experiments on MNIST, SVHN, and CelebA demonstrate, quantitatively and qualitatively, that dpVAE fixes sample generation for regularized VAEs.


page 7

page 8

page 14


Gromov-Wasserstein Autoencoders

Learning concise data representations without supervisory signals is a f...

Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions

Disentangled visual representations have largely been studied with gener...

Variational Lossy Autoencoder

Representation learning seeks to expose certain aspects of observed data...

Representation Learning for Non-Melanoma Skin Cancer using a Latent Autoencoder

Generative learning is a powerful tool for representation learning, and ...

Progressive Learning and Disentanglement of Hierarchical Representations

Learning rich representation from data is an important task for deep gen...

Recent Advances in Autoencoder-Based Representation Learning

Learning useful representations with little or no supervision is a key c...

Code Repositories