# Continuous Conditional Generative Adversarial Networks (cGAN) with Generator Regularization

arXiv: https://arxiv.org/abs/2103.14884 · HTML: https://mlsanity.com/paper/2103.14884/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 27 Mar 2021.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [Toward Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1711.11586/) (2017)
- [cGANs with Projection Discriminator](https://mlsanity.com/paper/1802.05637/) (2018)
- [MirrorGAN: Learning Text-to-image Generation by Redescription](https://mlsanity.com/paper/1903.05854/) (2019)
- [Latent Space Oddity: on the Curvature of Deep Generative Models](https://mlsanity.com/paper/1710.11379/) (2017)
- [Consistency Regularization for Generative Adversarial Networks](https://mlsanity.com/paper/1910.12027/) (2019)
- [Diversity-Sensitive Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1901.09024/) (2019)
- [Metrics for Deep Generative Models](https://mlsanity.com/paper/1711.01204/) (2017)
- [Gaussian Process Conditional Density Estimation](https://mlsanity.com/paper/1810.12750/) (2018)
- [Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling](https://mlsanity.com/paper/1904.02399/) (2019)

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

- [t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learning](https://mlsanity.com/paper/2202.10565/) (2022)
- [Learning to Simulate: Generative Metamodeling via Quantile Regression](https://mlsanity.com/paper/2311.17797/) (2023)
- [Parameters, Properties, and Process: Conditional Neural Generation of Realistic SEM Imagery Towards ML-assisted Advanced Manufacturing](https://mlsanity.com/paper/2302.08495/) (2023)

## Abstract (arXiv)

Conditional Generative Adversarial Networks are known to be difficult to train, especially when the conditions are continuous and high-dimensional. To partially alleviate this difficulty, we propose a simple generator regularization term on the GAN generator loss in the form of Lipschitz penalty. Thus, when the generator is fed with neighboring conditions in the continuous space, the regularization term will leverage the neighbor information and push the generator to generate samples that have similar conditional distributions for each neighboring condition. We analyze the effect of the proposed regularization term and demonstrate its robust performance on a range of synthetic and real-world tasks.