Improving Generative Adversarial Networks with Denoising Feature Matching
Abstract
We propose an augmented training procedure for generative adversarial networks designed to address shortcomings of the original by directing the generator towards probable configurations of abstract discriminator features. We estimate and track the distribution of these features, as computed from data, with a denoising auto-encoder, and use it to propose high-level targets for the generator. We combine this new loss with the original and evaluate the hybrid criterion on the task of unsupervised image synthesis from datasets comprising a diverse set of visual categories, noting a qualitative and quantitative improvement in the ``objectness'' of the resulting samples.
Cite
Text
Warde-Farley and Bengio. "Improving Generative Adversarial Networks with Denoising Feature Matching." International Conference on Learning Representations, 2017.Markdown
[Warde-Farley and Bengio. "Improving Generative Adversarial Networks with Denoising Feature Matching." International Conference on Learning Representations, 2017.](https://mlanthology.org/iclr/2017/wardefarley2017iclr-improving/)BibTeX
@inproceedings{wardefarley2017iclr-improving,
title = {{Improving Generative Adversarial Networks with Denoising Feature Matching}},
author = {Warde-Farley, David and Bengio, Yoshua},
booktitle = {International Conference on Learning Representations},
year = {2017},
url = {https://mlanthology.org/iclr/2017/wardefarley2017iclr-improving/}
}