In this paper we propose a new semi-supervised GAN architecture (ss-InfoGAN) for image synthesis that leverages information from few labels (as little as 0.22%, max. 10% of the dataset) to learn semantically meaningful and controllable data representations where latent variables correspond to label categories. The architecture builds on Information Maximizing Generative Adversarial Networks (InfoGAN) and is shown to learn both continuous and categorical codes and achieves higher quality of synthetic samples compared to fully unsupervised settings. Furthermore, we show that using small amounts of labeled data speeds-up training convergence. The architecture maintains the ability to disentangle latent variables for which no labels are available. Finally, we contribute an information-theoretic reasoning on how introducing semi-supervision increases mutual information between synthetic and real data.

本文提出了一种新的半监督 GAN 架构 (ss-InfoGAN)，用于图像合成，可以利用少量标签（最多不超过数据集的 10%）的信息学习语义有意义的和可控制的数据表示，其中潜变量对应标签类别，该架构建立在信息最大化生成对抗网络 (InfoGAN) 的基础上，被证明可以学习连续和分类编码，并实现比完全无监督设置更高质量的合成样本。此外，我们表明，使用少量标记数据可以加快训练收敛速度。最后，本文贡献了关于介绍半监督增加合成数据和真实数据之间的互信息的信息理论推理。

用半监督引导 InfoGAN