Implicit Modeling — A Generalization of Discriminative and Generative Approaches

Dr. Dmitrij Schlesinger
Germany, Dresden University of Technology
We propose a new modeling approach that is a generalization of generative and discriminative models. The core idea is to use an implicit parameterization of a joint probability distribution by specifying only the conditional distributions. The proposed scheme combines the advantages of both worlds – it can use powerful complex discriminative models as its parts having at the same time better generalization capabilities. We thoroughly evaluate the proposed model for a simple classification task with artificial data and achieve promising results for the semantic image segmentation problem.