# Transferring Unconditional to Conditional GANs with Hyper-Modulation

arXiv: https://arxiv.org/abs/2112.02219 · HTML: https://mlsanity.com/paper/2112.02219/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 60 references that are in the map.
- First posted on arXiv 4 Dec 2021.

## Builds on (most cited first, 30 of 49)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Reliable Fidelity and Diversity Metrics for Generative Models](https://mlsanity.com/paper/2002.09797/) (2020)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [In-Domain GAN Inversion for Real Image Editing](https://mlsanity.com/paper/2004.00049/) (2020)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning](https://mlsanity.com/paper/1903.10258/) (2019)
- [Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks](https://mlsanity.com/paper/1506.05751/) (2015)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [Adversarial Generation of Continuous Images](https://mlsanity.com/paper/2011.12026/) (2020)
- [Transferring GANs: generating images from limited data](https://mlsanity.com/paper/1805.01677/) (2018)
- [Graph HyperNetworks for Neural Architecture Search](https://mlsanity.com/paper/1810.05749/) (2018)

## Built on by (most cited first, 4 of 4)

- [Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generation](https://mlsanity.com/paper/2311.08217/) (2023)
- [Clustered Saliency Prediction](https://mlsanity.com/paper/2207.02205/) (2022)
- [GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomes](https://mlsanity.com/paper/2509.22953/) (2025)
- [Large-Scale Public Data Improves Differentially Private Image Generation Quality](https://mlsanity.com/paper/2309.00008/) (2023)

## Abstract (arXiv)

GANs have matured in recent years and are able to generate high-resolution, realistic images. However, the computational resources and the data required for the training of high-quality GANs are enormous, and the study of transfer learning of these models is therefore an urgent topic. Many of the available high-quality pretrained GANs are unconditional (like StyleGAN). For many applications, however, conditional GANs are preferable, because they provide more control over the generation process, despite often suffering more training difficulties. Therefore, in this paper, we focus on transferring from high-quality pretrained unconditional GANs to conditional GANs. This requires architectural adaptation of the pretrained GAN to perform the conditioning. To this end, we propose hyper-modulated generative networks that allow for shared and complementary supervision. To prevent the additional weights of the hypernetwork to overfit, with subsequent mode collapse on small target domains, we introduce a self-initialization procedure that does not require any real data to initialize the hypernetwork parameters. To further improve the sample efficiency of the transfer, we apply contrastive learning in the discriminator, which effectively works on very limited batch sizes. In extensive experiments, we validate the efficiency of the hypernetworks, self-initialization and contrastive loss for knowledge transfer on standard benchmarks.