It Takes (Only) Two: Adversarial Generator-Encoder Networks

Authors

  • Dmitry Ulyanov Skolkovo Institute of Science and Technology, Yandex
  • Andrea Vedaldi University of Oxford
  • Victor Lempitsky Skolkovo Institute of Science and Technology

Keywords:

adversarial learning

Abstract

We present a new autoencoder-type architecture that is trainable in an unsupervised mode, sustains both generation and inference, and has the quality of conditional and unconditional samples boosted by adversarial learning. Unlike previous hybrids of autoencoders and adversarial networks, the adversarial game in our approach is set up directly between the encoder and the generator, and no external mappings are trained in the process of learning.The game objective compares the divergences of each of the real and the generated data distributions with the prior distribution in the latent space. We show that direct generator-vs-encoder game leads to a tight coupling of the two components, resulting in samples and reconstructions of a comparable quality to some recently-proposed more complex architectures.

Downloads

Published

2018-04-25

How to Cite

Ulyanov, D., Vedaldi, A., & Lempitsky, V. (2018). It Takes (Only) Two: Adversarial Generator-Encoder Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11449

Issue

Section

AAAI Technical Track: Game Theory and Economic Paradigms