Rate-Regularization and Generalization in VAEs
Variational autoencoders (VAEs) optimize an objective that comprises a reconstruction loss (the distortion) and a KL term (the rate). The rate is an upper bound on the mutual …
Deep Representation Learning for Complex Medical Images
The performance of any task depends on the representation of the data. A good representation should capture the factors of variation relevant to the task at hand while discarding …
Structured Disentagled Representations
Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner. A number of recent efforts have focused on learning representations that …
babak-esmaeili
Can VAEs generate novel examples?
An implicit goal in works on deep generative models is that such models should be able to generate novel examples that were not previously seen in the training data. In this paper, …