# Self-labeled Conditional GANs

arXiv: https://arxiv.org/abs/2012.02162 · HTML: https://mlsanity.com/paper/2012.02162/

## Key facts

- Cited by 8 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 8 of 8)

- [Instance-Conditioned GAN](https://mlsanity.com/paper/2109.05070/) (2021)
- [Normalizing Flows are Capable Generative Models](https://mlsanity.com/paper/2412.06329/) (2024)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels](https://mlsanity.com/paper/2302.10586/) (2023)
- [Why Are Conditional Generative Models Better Than Unconditional Ones?](https://mlsanity.com/paper/2212.00362/) (2022)
- [Guidance Free Image Editing via Explicit Conditioning](https://mlsanity.com/paper/2503.17593/) (2025)
- [A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention](https://mlsanity.com/paper/2106.09914/) (2021)
- [Unifying conditional and unconditional semantic image synthesis with OCO-GAN](https://mlsanity.com/paper/2211.14105/) (2022)

## Abstract (arXiv)

This paper introduces a novel and fully unsupervised framework for conditional GAN training in which labels are automatically obtained from data. We incorporate a clustering network into the standard conditional GAN framework that plays against the discriminator. With the generator, it aims to find a shared structured mapping for associating pseudo-labels with the real and fake images. Our generator outperforms unconditional GANs in terms of FID with significant margins on large scale datasets like ImageNet and LSUN. It also outperforms class conditional GANs trained on human labels on CIFAR10 and CIFAR100 where fine-grained annotations or a large number of samples per class are not available. Additionally, our clustering network exceeds the state-of-the-art on CIFAR100 clustering.