# When, Why, and Which Pretrained GANs Are Useful?

arXiv: https://arxiv.org/abs/2202.08937 · HTML: https://mlsanity.com/paper/2202.08937/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 30 references that are in the map.
- First posted on arXiv 17 Feb 2022.

## Builds on (most cited first, 26 of 26)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [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)
- [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Video-to-Video Synthesis](https://mlsanity.com/paper/1808.06601/) (2018)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [Unsupervised Discovery of Interpretable Directions in the GAN Latent Space](https://mlsanity.com/paper/2002.03754/) (2020)
- [DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort](https://mlsanity.com/paper/2104.06490/) (2021)
- [Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation](https://mlsanity.com/paper/2003.13659/) (2020)
- [Transferring GANs: generating images from limited data](https://mlsanity.com/paper/1805.01677/) (2018)
- [Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs](https://mlsanity.com/paper/2002.10964/) (2020)
- [Few-shot Image Generation with Elastic Weight Consolidation](https://mlsanity.com/paper/2012.02780/) (2020)
- [MineGAN: effective knowledge transfer from GANs to target domains with few images](https://mlsanity.com/paper/1912.05270/) (2019)
- [Image Generation From Small Datasets via Batch Statistics Adaptation](https://mlsanity.com/paper/1904.01774/) (2019)
- [On Leveraging Pretrained GANs for Generation with Limited Data](https://mlsanity.com/paper/2002.11810/) (2020)

## Built on by (most cited first, 14 of 14)

- [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023)
- [Vision-Language Pre-training: Basics, Recent Advances, and Future Trends](https://mlsanity.com/paper/2210.09263/) (2022)
- [UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation](https://mlsanity.com/paper/2203.02557/) (2022)
- [A Comprehensive Survey on Data-Efficient GANs in Image Generation](https://mlsanity.com/paper/2204.08329/) (2022)
- [A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot](https://mlsanity.com/paper/2307.14397/) (2023)
- [FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs](https://mlsanity.com/paper/2207.08630/) (2022)
- [Content-Based Search for Deep Generative Models](https://mlsanity.com/paper/2210.03116/) (2022)
- [Semi-supervised domain adaptation with CycleGAN guided by a downstream task loss](https://mlsanity.com/paper/2208.08815/) (2022)
- [UGC: Unified GAN Compression for Efficient Image-to-Image Translation](https://mlsanity.com/paper/2309.09310/) (2023)
- [Restyling Unsupervised Concept Based Interpretable Networks with Generative Models](https://mlsanity.com/paper/2407.01331/) (2024)
- [Geometry aware 3D generation from in-the-wild images in ImageNet](https://mlsanity.com/paper/2402.00225/) (2024)
- [Conditional Diffusion on Web-Scale Image Pairs leads to Diverse Image Variations](https://mlsanity.com/paper/2405.14857/) (2024)
- [DiffGAN: A Test Generation Approach for Differential Testing of Deep Neural Networks for Image Analysis](https://mlsanity.com/paper/2410.19794/) (2024)
- [Generative AI-Driven High-Fidelity Human Motion Simulation](https://mlsanity.com/paper/2507.14097/) (2025)

## Abstract (arXiv)

The literature has proposed several methods to finetune pretrained GANs on new datasets, which typically results in higher performance compared to training from scratch, especially in the limited-data regime. However, despite the apparent empirical benefits of GAN pretraining, its inner mechanisms were not analyzed in-depth, and understanding of its role is not entirely clear. Moreover, the essential practical details, e.g., selecting a proper pretrained GAN checkpoint, currently do not have rigorous grounding and are typically determined by trial and error. This work aims to dissect the process of GAN finetuning. First, we show that initializing the GAN training process by a pretrained checkpoint primarily affects the model's coverage rather than the fidelity of individual samples. Second, we explicitly describe how pretrained generators and discriminators contribute to the finetuning process and explain the previous evidence on the importance of pretraining both of them. Finally, as an immediate practical benefit of our analysis, we describe a simple recipe to choose an appropriate GAN checkpoint that is the most suitable for finetuning to a particular target task. Importantly, for most of the target tasks, Imagenet-pretrained GAN, despite having poor visual quality, appears to be an excellent starting point for finetuning, resembling the typical pretraining scenario of discriminative computer vision models.