# Searching towards Class-Aware Generators for Conditional Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2006.14208 · HTML: https://mlsanity.com/paper/2006.14208/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2020.

## Built on by (most cited first, 6 of 6)

- [MirrorDiffusion: Stabilizing Diffusion Process in Zero-shot Image Translation by Prompts Redescription and Beyond](https://mlsanity.com/paper/2401.03221/) (2024)
- [Are conditional GANs explicitly conditional?](https://mlsanity.com/paper/2106.15011/) (2021)
- [Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data](https://mlsanity.com/paper/2102.10485/) (2021)
- [Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks](https://mlsanity.com/paper/2207.12315/) (2022)
- [On depth prediction for autonomous driving using self-supervised learning](https://mlsanity.com/paper/2403.06194/) (2024)
- [Neural Architecture Search for Generative Adversarial Networks: A Comprehensive Review and Critical Analysis](https://mlsanity.com/paper/2606.26169/) (2026)

## Abstract (arXiv)

Conditional Generative Adversarial Networks (cGAN) were designed to generate images based on the provided conditions, eg, class-level distributions. However, existing methods have used the same generating architecture for all classes. This paper presents a novel idea that adopts NAS to find a distinct architecture for each class. The search space contains regular and class-modulated convolutions, where the latter is designed to introduce class-specific information while avoiding the reduction of training data for each class generator. The search algorithm follows a weight-sharing pipeline with mixed-architecture optimization so that the search cost does not grow with the number of classes. To learn the sampling policy, a Markov decision process is embedded into the search algorithm and a moving average is applied for better stability. We evaluate our approach on CIFAR10 and CIFAR100. Besides achieving better image generation quality in terms of FID scores, we discover several insights that are helpful in designing cGAN models. Code is available at https://github.com/PeterouZh/NAScGAN.