# DAWSON: A Domain Adaptive Few Shot Generation Framework

arXiv: https://arxiv.org/abs/2001.00576 · HTML: https://mlsanity.com/paper/2001.00576/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jan 2020.

## Built on by (most cited first, 27 of 27)

- [Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment](https://mlsanity.com/paper/2203.04121/) (2022)
- [Zero-shot Generative Model Adaptation via Image-specific Prompt Learning](https://mlsanity.com/paper/2304.03119/) (2023)
- [WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generation](https://mlsanity.com/paper/2207.07288/) (2022)
- [The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation](https://mlsanity.com/paper/2211.12347/) (2022)
- [Learning Prototype-oriented Set Representations for Meta-Learning](https://mlsanity.com/paper/2110.09140/) (2021)
- [A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot](https://mlsanity.com/paper/2307.14397/) (2023)
- [Attribute Group Editing for Reliable Few-shot Image Generation](https://mlsanity.com/paper/2203.08422/) (2022)
- [Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption](https://mlsanity.com/paper/2309.03729/) (2023)
- [Image Synthesis under Limited Data: A Survey and Taxonomy](https://mlsanity.com/paper/2307.16879/) (2023)
- [Few-shot Image Generation Using Discrete Content Representation](https://mlsanity.com/paper/2207.10833/) (2022)
- [Stable Attribute Group Editing for Reliable Few-shot Image Generation](https://mlsanity.com/paper/2302.00179/) (2023)
- [Domain Adaptive Few-Shot Open-Set Learning](https://mlsanity.com/paper/2309.12814/) (2023)
- [HypDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-shot Image Generation](https://mlsanity.com/paper/2411.17784/) (2024)
- [Cross-modulated Few-shot Image Generation for Colorectal Tissue Classification](https://mlsanity.com/paper/2304.01992/) (2023)
- [MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces](https://mlsanity.com/paper/2309.08113/) (2023)
- [Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation](https://mlsanity.com/paper/2212.07886/) (2022)
- [STORM-GAN: Spatio-Temporal Meta-GAN for Cross-City Estimation of Human Mobility Responses to COVID-19](https://mlsanity.com/paper/2301.08648/) (2023)
- [Few-shot Implicit Function Generation via Equivariance](https://mlsanity.com/paper/2501.01601/) (2025)
- [Overcoming challenges in leveraging GANs for few-shot data augmentation](https://mlsanity.com/paper/2203.16662/) (2022)
- [D3T-GAN: Data-Dependent Domain Transfer GANs for Few-shot Image Generation](https://mlsanity.com/paper/2205.06032/) (2022)
- [DEff-GAN: Diverse Attribute Transfer for Few-Shot Image Synthesis](https://mlsanity.com/paper/2302.14533/) (2023)
- [Conditional Distribution Modelling for Few-Shot Image Synthesis with Diffusion Models](https://mlsanity.com/paper/2404.16556/) (2024)
- [Dual Path Structural Contrastive Embeddings for Learning Novel Objects](https://mlsanity.com/paper/2112.12359/) (2021)
- [DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta](https://mlsanity.com/paper/2207.10271/) (2022)
- [EqGAN: Feature Equalization Fusion for Few-shot Image Generation](https://mlsanity.com/paper/2307.14638/) (2023)
- [Improving Few-shot Image Generation by Structural Discrimination and Textural Modulation](https://mlsanity.com/paper/2308.16110/) (2023)
- [TAGE: Trustworthy Attribute Group Editing for Stable Few-shot Image Generation](https://mlsanity.com/paper/2410.17855/) (2024)

## Abstract (arXiv)

Training a Generative Adversarial Networks (GAN) for a new domain from scratch requires an enormous amount of training data and days of training time. To this end, we propose DAWSON, a Domain Adaptive FewShot Generation FrameworkFor GANs based on meta-learning. A major challenge of applying meta-learning GANs is to obtain gradients for the generator from evaluating it on development sets due to the likelihood-free nature of GANs. To address this challenge, we propose an alternative GAN training procedure that naturally combines the two-step training procedure of GANs and the two-step training procedure of meta-learning algorithms. DAWSON is a plug-and-play framework that supports a broad family of meta-learning algorithms and various GANs with architectural-variants. Based on DAWSON, We also propose MUSIC MATINEE, which is the first few-shot music generation model. Our experiments show that MUSIC MATINEE could quickly adapt to new domains with only tens of songs from the target domains. We also show that DAWSON can learn to generate new digits with only four samples in the MNIST dataset. We release source codes implementation of DAWSON in both PyTorch and Tensorflow, generated music samples on two genres and the lightning video.