Deep Multivariate Models with Parametric Conditionals
This addresses the limitation of task-specific models in computer vision by providing a flexible framework for broader applicability, though it is incremental in its approach.
The paper tackles the problem of developing deep multivariate models for heterogeneous data collections by proposing a joint probability representation using conditional distributions for each variable group, enabling applicability to any downstream task and supporting semi-supervised learning through likelihood maximization.
We consider deep multivariate models for heterogeneous collections of random variables. In the context of computer vision, such collections may e.g. consist of images, segmentations, image attributes, and latent variables. When developing such models, most existing works start from an application task and design the model components and their dependencies to meet the needs of the chosen task. This has the disadvantage of limiting the applicability of the resulting model for other downstream tasks. Here, instead, we propose to represent the joint probability distribution by means of conditional probability distributions for each group of variables conditioned on the rest. Such models can then be used for practically any possible downstream task. Their learning can be approached as training a parametrised Markov chain kernel by maximising the data likelihood of its limiting distribution. This has the additional advantage of allowing a wide range of semi-supervised learning scenarios.