# Semi-supervised Conditional GANs

arXiv: https://arxiv.org/abs/1708.05789 · HTML: https://mlsanity.com/paper/1708.05789/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2017.

## Built on by (most cited first, 3 of 3)

- [OSSGAN: Open-Set Semi-Supervised Image Generation](https://mlsanity.com/paper/2204.14249/) (2022)
- [Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers](https://mlsanity.com/paper/2603.27666/) (2026)
- [Overcoming challenges in leveraging GANs for few-shot data augmentation](https://mlsanity.com/paper/2203.16662/) (2022)

## Abstract (arXiv)

We introduce a new model for building conditional generative models in a semi-supervised setting to conditionally generate data given attributes by adapting the GAN framework. The proposed semi-supervised GAN (SS-GAN) model uses a pair of stacked discriminators to learn the marginal distribution of the data, and the conditional distribution of the attributes given the data respectively. In the semi-supervised setting, the marginal distribution (which is often harder to learn) is learned from the labeled + unlabeled data, and the conditional distribution is learned purely from the labeled data. Our experimental results demonstrate that this model performs significantly better compared to existing semi-supervised conditional GAN models.