arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.01583stat.MLcs.LG
收藏

基于生成对抗网络的半监督学习

Semi-Supervised Learning with Generative Adversarial Networks

Augustus Odena

摘要:

我们将生成对抗网络(GANs)扩展到半监督上下文,迫使生成对抗网络输出类标签。我们训练一个生成模型G和一个具有属于N个类之一的输入的数据集上的一个生成模型D。在训练时,D被用来预测输入属于N+1个类中的哪一个,其中添加额外的类以对应于G的输出。我们表明,这种方法可以用来创建一个更有效的数据分类器,它允许生成更高质量的样本比常规的GAN。

英文摘要:

We extend Generative Adversarial Networks (GANs) to the semi-supervised context by forcing the discriminator network to output class labels. We train a generative model G and a discriminator D on a dataset with inputs belonging to one of N classes. At training time, D is made to predict which of N+1 classes the input belongs to, where an extra class is added to correspond to the outputs of G. We show that this method can be used to create a more data-efficient classifier and that it allows for generating higher quality samples than a regular GAN.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑