… Generative modeling of data is a challenging machine learning problem that has … of
generative adversarial networks (GANs) [5] and its several sophisticated variants 1. A GAN model is …

… of typical discriminative models, ie, convolutional neural networks. In this paper, we further
introduce and adapt the concept of capsules to generative models. Generative models have …

… We propose a generative model to … capsules; for example, Li & Zhu (2019) develop a capsule
restricted Boltzmann machine (RBM). This generative model contains a number of capsules…

… In this paper we specify a generative model for such data, and derive a variational algorithm
for inferring the transformation of each object and the assignments of observed parts to the …

… use generative models to synthesise more data. To this end, we introduce CapsPix2Pix, which
combines convolutional capsules … As the end goal of our work on generative models is to …

… capsule routing algorithm utilizing iterative inference under sparsity constraints. We then
introduce an explicit probabilistic generative model for capsule … generative model for capsules …

… they aim to model a range of … of capsules in deep generative models. In this study, to
address this challenge, we present a statistical modelling of capsules in deep generative models …

… , is a neural network that outputs the probability that the input is a (x) D sample from the
same data distribution (positive samples), or whether it is a sample from our generative model (…

… Generative Adversarial Networks [4] are finding popular applications as generative models
in diverse scenarios. One of the biggest advantages of GANs is that they can be trained …

… presented without specification of a corresponding generative model for the data (with the
… for a generative approach to model the relationships of objects and their parts in capsule …