# DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domains

arXiv: https://arxiv.org/abs/2211.14554 · HTML: https://mlsanity.com/paper/2211.14554/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 53 references that are in the map.
- First posted on arXiv 26 Nov 2022.

## Builds on (most cited first, 30 of 47)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [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)
- [In-Domain GAN Inversion for Real Image Editing](https://mlsanity.com/paper/2004.00049/) (2020)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [Towards Real-World Blind Face Restoration with Generative Facial Prior](https://mlsanity.com/paper/2101.04061/) (2021)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)
- [Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks](https://mlsanity.com/paper/2106.04489/) (2021)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing](https://mlsanity.com/paper/2111.15666/) (2021)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [GAN Prior Embedded Network for Blind Face Restoration in the Wild](https://mlsanity.com/paper/2105.06070/) (2021)
- [StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators](https://mlsanity.com/paper/2108.00946/) (2021)

## Built on by (most cited first, 15 of 15)

- [A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot](https://mlsanity.com/paper/2307.14397/) (2023)
- [Domain Re-Modulation for Few-Shot Generative Domain Adaptation](https://mlsanity.com/paper/2302.02550/) (2023)
- [Portrait Diffusion: Training-free Face Stylization with Chain-of-Painting](https://mlsanity.com/paper/2312.02212/) (2023)
- [CLIPtone: Unsupervised Learning for Text-based Image Tone Adjustment](https://mlsanity.com/paper/2404.01123/) (2024)
- [Image Synthesis under Limited Data: A Survey and Taxonomy](https://mlsanity.com/paper/2307.16879/) (2023)
- [Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generation](https://mlsanity.com/paper/2311.08217/) (2023)
- [Stylized Face Sketch Extraction via Generative Prior with Limited Data](https://mlsanity.com/paper/2403.11263/) (2024)
- [LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example](https://mlsanity.com/paper/2403.15227/) (2024)
- [One-shot Generative Domain Adaptation in 3D GANs](https://mlsanity.com/paper/2410.08824/) (2024)
- [ZePo: Zero-Shot Portrait Stylization with Faster Sampling](https://mlsanity.com/paper/2408.05492/) (2024)
- [Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations](https://mlsanity.com/paper/2308.10554/) (2023)
- [Non-Visible Light Data Synthesis and Application: A Case Study for Synthetic Aperture Radar Imagery](https://mlsanity.com/paper/2311.17486/) (2023)
- [HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation](https://mlsanity.com/paper/2411.12832/) (2024)
- [StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition](https://mlsanity.com/paper/2604.21689/) (2026)
- [Few-Shot Generative Model Adaption via Identity Injection and Preservation](https://mlsanity.com/paper/2603.22965/) (2026)

## Abstract (arXiv)

Few-shot domain adaptation to multiple domains aims to learn a complex image distribution across multiple domains from a few training images. A na"ive solution here is to train a separate model for each domain using few-shot domain adaptation methods. Unfortunately, this approach mandates linearly-scaled computational resources both in memory and computation time and, more importantly, such separate models cannot exploit the shared knowledge between target domains. In this paper, we propose DynaGAN, a novel few-shot domain-adaptation method for multiple target domains. DynaGAN has an adaptation module, which is a hyper-network that dynamically adapts a pretrained GAN model into the multiple target domains. Hence, we can fully exploit the shared knowledge across target domains and avoid the linearly-scaled computational requirements. As it is still computationally challenging to adapt a large-size GAN model, we design our adaptation module light-weight using the rank-1 tensor decomposition. Lastly, we propose a contrastive-adaptation loss suitable for multi-domain few-shot adaptation. We validate the effectiveness of our method through extensive qualitative and quantitative evaluations.