# Diverse Image Generation via Self-Conditioned GANs

arXiv: https://arxiv.org/abs/2006.10728 · HTML: https://mlsanity.com/paper/2006.10728/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2020.

## Built on by (most cited first, 30 of 55)

- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis](https://mlsanity.com/paper/2211.09117/) (2022)
- [TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data](https://mlsanity.com/paper/2201.07284/) (2022)
- [Instance-Conditioned GAN](https://mlsanity.com/paper/2109.05070/) (2021)
- [Return of Unconditional Generation: A Self-supervised Representation Generation Method](https://mlsanity.com/paper/2312.03701/) (2023)
- [Improved Transformer for High-Resolution GANs](https://mlsanity.com/paper/2106.07631/) (2021)
- [Diffusion Models and Representation Learning: A Survey](https://mlsanity.com/paper/2407.00783/) (2024)
- [On Aliased Resizing and Surprising Subtleties in GAN Evaluation](https://mlsanity.com/paper/2104.11222/) (2021)
- [Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models](https://mlsanity.com/paper/2105.08127/) (2021)
- [Self-Distilled StyleGAN: Towards Generation from Internet Photos](https://mlsanity.com/paper/2202.12211/) (2022)
- [Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels](https://mlsanity.com/paper/2302.10586/) (2023)
- [State-of-the-Art in the Architecture, Methods and Applications of StyleGAN](https://mlsanity.com/paper/2202.14020/) (2022)
- [Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective](https://mlsanity.com/paper/2103.00397/) (2021)
- [KD-DLGAN: Data Limited Image Generation via Knowledge Distillation](https://mlsanity.com/paper/2303.17158/) (2023)
- [GenCo: Generative Co-training for Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2110.01254/) (2021)
- [Diffusion Posterior Proximal Sampling for Image Restoration](https://mlsanity.com/paper/2402.16907/) (2024)
- [MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators](https://mlsanity.com/paper/2107.07260/) (2021)
- [Secure Federated Clustering](https://mlsanity.com/paper/2205.15564/) (2022)
- [Partition-Guided GANs](https://mlsanity.com/paper/2104.00816/) (2021)
- [Contrastive Fine-grained Class Clustering via Generative Adversarial Networks](https://mlsanity.com/paper/2112.14971/) (2021)
- [Improved Input Reprogramming for GAN Conditioning](https://mlsanity.com/paper/2201.02692/) (2022)
- [Unsupervised Learning of Structured Representations via Closed-Loop Transcription](https://mlsanity.com/paper/2210.16782/) (2022)
- [Do DALL-E and Flamingo Understand Each Other?](https://mlsanity.com/paper/2212.12249/) (2022)
- [Learning Profitable NFT Image Diffusions via Multiple Visual-Policy Guided Reinforcement Learning](https://mlsanity.com/paper/2306.11731/) (2023)
- [Ensembles of GANs for synthetic training data generation](https://mlsanity.com/paper/2104.11797/) (2021)
- [Self-Conditioned Generative Adversarial Networks for Image Editing](https://mlsanity.com/paper/2202.04040/) (2022)
- [LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data](https://mlsanity.com/paper/2208.14889/) (2022)

## Abstract (arXiv)

We introduce a simple but effective unsupervised method for generating realistic and diverse images. We train a class-conditional GAN model without using manually annotated class labels. Instead, our model is conditional on labels automatically derived from clustering in the discriminator's feature space. Our clustering step automatically discovers diverse modes, and explicitly requires the generator to cover them. Experiments on standard mode collapse benchmarks show that our method outperforms several competing methods when addressing mode collapse. Our method also performs well on large-scale datasets such as ImageNet and Places365, improving both image diversity and standard quality metrics, compared to previous methods.