mlsanityData to 7 Oct 2026

Few-Shot Adaptation of Generative Adversarial Networks

arXiv 2010.11943 ↗First posted 22 Oct 2020cs.CVcited by 64

Not on the map. Why?

Abstract (arXiv)

Generative Adversarial Networks (GANs) have shown remarkable performance in image synthesis tasks, but typically require a large number of training samples to achieve high-quality synthesis. This paper proposes a simple and effective method, Few-Shot GAN (FSGAN), for adapting GANs in few-shot settings (less than 100 images). FSGAN repurposes component analysis techniques and learns to adapt the singular values of the pre-trained weights while freezing the corresponding singular vectors. This provides a highly expressive parameter space for adaptation while constraining changes to the pretrained weights. We validate our method in a challenging few-shot setting of 5-100 images in the target domain. We show that our method has significant visual quality gains compared with existing GAN adaptation methods. We report qualitative and quantitative results showing the effectiveness of our method. We additionally highlight a problem for few-shot synthesis in the standard quantitative metric used by data-efficient image synthesis works. Code and additional results are available at http://e-271.github.io/few-shot-gan.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 21; 2023: 22; 2024: 10; 2025: 1; 2026: 1.

64 papers.

Sort:

By area:

  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  2. 2023SVDiff: Compact Parameter Space for Diffusion Fine-Tuningcited by 338
  3. 2021Projected GANs Converge Fastercited by 204
  4. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  5. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  6. 2023Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluationcited by 108
  7. 2023Few-Shot Defect Image Generation via Defect-Aware Feature Manipulationcited by 66
  8. 2022Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignmentcited by 54
  9. 2021JoJoGAN: One Shot Face Stylizationcited by 49
  10. 2021One-Shot Generative Domain Adaptationcited by 41
  11. 2022Diffusion Guided Domain Adaptation of Image Generatorscited by 35
  12. 2022DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Modelcited by 32
38 more
  1. 2022One-Shot Adaptation of GAN in Just One CLIPcited by 31
  2. 2023Zero-shot Generative Model Adaptation via Image-specific Prompt Learningcited by 27
  3. 2022MyStyle: A Personalized Generative Priorcited by 26
  4. 2021Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspectivecited by 25
  5. 2022Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networkscited by 23
  6. 2024Spectral Adapter: Fine-Tuning in Spectral Spacecited by 21
  7. 2022A Comprehensive Survey on Data-Efficient GANs in Image Generationcited by 20
  8. 2022Generalized One-shot Domain Adaptation of Generative Adversarial Networkscited by 19
  9. 2022HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networkscited by 19
  10. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
  11. 2023Domain Re-Modulation for Few-Shot Generative Domain Adaptationcited by 18
  12. 2021Few-shot Image Generation with Mixup-based Distance Learningcited by 16
  13. 2023Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translationcited by 15
  14. 2022Few-shot Image Generation via Masked Discriminationcited by 12
  15. 2023WeditGAN: Few-Shot Image Generation via Latent Space Relocationcited by 12
  16. 2022StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptationcited by 10
  17. 2023Portrait Diffusion: Training-free Face Stylization with Chain-of-Paintingcited by 10
  18. 2023DemoCaricature: Democratising Caricature Generation with a Rough Sketchcited by 10
  19. 2024PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank Reductioncited by 10
  20. 2024KIND: Knowledge Integration and Diversion for Training Decomposable Modelscited by 10
  21. 2021CharacterGAN: Few-Shot Keypoint Character Animation and Reposingcited by 9
  22. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  23. 2021Generating Novel Scene Compositions from Single Images and Videoscited by 8
  24. 2022MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequencescited by 8
  25. 2022Few-shot Image Generation Using Discrete Content Representationcited by 6
  26. 2023Text-driven Visual Synthesis with Latent Diffusion Priorcited by 6
  27. 2023SAVE: Spectral-Shift-Aware Adaptation of Image Diffusion Models for Text-driven Video Editingcited by 5
  28. 2023Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generationcited by 5
  29. 2022One-Shot Synthesis of Images and Segmentation Maskscited by 4
  30. 2022Exploring Spatial-Temporal Features for Deepfake Detection and Localizationcited by 4
  31. 2023Few-shot Semantic Image Synthesis with Class Affinity Transfercited by 4
  32. 2023Improving the Effectiveness of Deep Generative Datacited by 4
  33. 2023Smoothness Similarity Regularization for Few-Shot GAN Adaptationcited by 3
  34. 2024Exploring the Potentials and Challenges of Deep Generative Models in Product Design Conceptioncited by 3
  35. 2022Dual-Domain Image Synthesis using Segmentation-Guided GANcited by 2
  36. 2024Seizing the Means of Production: Exploring the Landscape of Crafting, Adapting and Navigating Generative AI Models in the Visual Artscited by 2
  37. 2024ZePo: Zero-Shot Portrait Stylization with Faster Samplingcited by 2
  38. 2022Overcoming challenges in leveraging GANs for few-shot data augmentationcited by 1

50 most cited of 64 All 64 (JSON)