Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions
Machine Learning
2019-04-24 v3 Machine Learning
Abstract
We present a neural network architecture based upon the Autoencoder (AE) and Generative Adversarial Network (GAN) that promotes a convex latent distribution by training adversarially on latent space interpolations. By using an AE as both the generator and discriminator of a GAN, we pass a pixel-wise error function across the discriminator, yielding an AE which produces non-blurry samples that match both high- and low-level features of the original images. Interpolations between images in this space remain within the latent-space distribution of real images as trained by the discriminator, and therfore preserve realistic resemblances to the network inputs. Code available at https://github.com/timsainb/GAIA
Cite
@article{arxiv.1807.06650,
title = {Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions},
author = {Tim Sainburg and Marvin Thielk and Brad Theilman and Benjamin Migliori and Timothy Gentner},
journal= {arXiv preprint arXiv:1807.06650},
year = {2019}
}