Implicit Modeling -- A Generalization of Discriminative and Generative Approaches
This work addresses the problem of improving model generalization in machine learning by bridging generative and discriminative approaches, though it appears incremental as it builds on existing paradigms.
The authors introduced a new modeling approach that generalizes generative and discriminative models by using an implicit parameterization of joint probability distributions through conditional distributions, combining the advantages of both to improve generalization capabilities. They evaluated it on a simple classification task with artificial data and demonstrated its benefits for semantic image segmentation in real-world scenarios.
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 method for a simple classification task with artificial data and illustrate its advantages for real-word scenarios on a semantic image segmentation problem.