Improved Techniques for Training GANs

来自 arXiv.org

喜欢 0

阅读量：

5232

作者：

T Salimans，I Goodfellow，W Zaremba，V Cheung，A Radford，X Chen

展开

摘要：

We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework. We focus on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic. Unlike most work on generative models, our primary goal is not to train a model that assigns high likelihood to test data, nor do we require the model to be able to learn well without using any labels. 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.

展开

关键词：

Computer Science - Machine Learning

DOI：

10.48550/arXiv.1606.03498

被引量：

1292

年份：

2016