Multi-view Generative Adversarial Networks

Mickaël Chen, Ludovic Denoyer

Nov 04, 2016 (modified: Dec 07, 2016) ICLR 2017 conference submission readers: everyone
  • Abstract: Learning over multi-view data is a challenging problem with strong practical applications. Most related studies focus on the classification point of view and assume that all the views are available at any time. We consider an extension of this framework in two directions. First, based on the BiGAN model, the Multi-view BiGAN (MV-BiGAN) is able to perform density estimation from multi-view inputs. Second, it can deal with missing views and is able to update its prediction when additional views are provided. We illustrate these properties on a set of experiments over different datasets.
  • TL;DR: We describe the MV-BiGAN model able to perform density estimation from multiple views, and to update its prediction when additional views are provided
  • Conflicts: lip6.fr
  • Keywords: Deep learning, Supervised Learning

Loading