Sampling Generative Networks

Tom White

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: vuw.ac.nz

Keywords: Unsupervised Learning, Deep learning, Computer vision

Community Implementations: [ 11 code implementations](https://www.catalyzex.com/paper/arxiv:1609.04468/code)