Sampling Generative Networks

Tom White

Nov 02, 2016 (modified: Dec 09, 2016) ICLR 2017 conference submission readers: everyone
  • Abstract: We introduce several techniques for sampling and visualizing the latent spaces of generative models. Replacing linear interpolation with spherical linear interpolation prevents diverging from a model's prior distribution and produces sharper samples. J-Diagrams and MINE grids are introduced as visualizations of manifolds created by analogies and nearest neighbors. We demonstrate two new techniques for deriving attribute vectors: bias-corrected vectors with data replication and synthetic vectors with data augmentation. Binary classification using attribute vectors is presented as a technique supporting quantitative analysis of the latent space. Most techniques are intended to be independent of model type and examples are shown on both Variational Autoencoders and Generative Adversarial Networks.
  • TL;DR: Demonstrates improved techniques for interpolation and deriving + evaluating attribute vectors in latent spaces applicable to both VAE and GAN models.
  • Conflicts:
  • Keywords: Unsupervised Learning, Deep learning, Computer vision