pith. sign in

arxiv: 1612.01397 · v1 · pith:XXJRQ7QTnew · submitted 2016-12-05 · 💻 cs.LG

Implicit Modeling -- A Generalization of Discriminative and Generative Approaches

classification 💻 cs.LG
keywords discriminativegeneralizationadvantagesgenerativeimplicitmodelingmodelsproposed
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.