Improved Techniques for Training GANs
Abstract
We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework. Using our new techniques, we achieve state-of-the-art results in semi-supervised classification on MNIST, CIFAR-10 and SVHN. The generated images are of high quality as confirmed by a visual Turing test: Our model generates MNIST samples that humans cannot distinguish from real data, and CIFAR-10 samples that yield a human error rate of 21.3%. We also present ImageNet samples with unprecedented resolution and show that our methods enable the model to learn recognizable features of ImageNet classes.
Cite
Text
Salimans et al. "Improved Techniques for Training GANs." Neural Information Processing Systems, 2016.Markdown
[Salimans et al. "Improved Techniques for Training GANs." Neural Information Processing Systems, 2016.](https://mlanthology.org/neurips/2016/salimans2016neurips-improved/)BibTeX
@inproceedings{salimans2016neurips-improved,
title = {{Improved Techniques for Training GANs}},
author = {Salimans, Tim and Goodfellow, Ian and Zaremba, Wojciech and Cheung, Vicki and Radford, Alec and Chen, Xi and Chen, Xi},
booktitle = {Neural Information Processing Systems},
year = {2016},
pages = {2234-2242},
url = {https://mlanthology.org/neurips/2016/salimans2016neurips-improved/}
}