mlsanityData to 14 Oct 2026

WeditGAN: Few-Shot Image Generation via Latent Space Relocation

arXiv 2305.06671 ↗First posted 11 May 2023cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

In few-shot image generation, directly training GAN models on just a handful of images faces the risk of overfitting. A popular solution is to transfer the models pretrained on large source domains to small target ones. In this work, we introduce WeditGAN, which realizes model transfer by editing the intermediate latent codes w in StyleGANs with learned constant offsets (Delta w), discovering and constructing target latent spaces via simply relocating the distribution of source latent spaces. The established one-to-one mapping between latent spaces can naturally prevents mode collapse and overfitting. Besides, we also propose variants of WeditGAN to further enhance the relocation process by regularizing the direction or finetuning the intensity of Delta w. Experiments on a collection of widely used source/target datasets manifest the capability of WeditGAN in generating realistic and diverse images, which is simple yet highly effective in the research area of few-shot image generation. Codes are available at https://github.com/Ldhlwh/WeditGAN.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 47 of its 57 references that are in the map. First posted on arXiv 11 May 2023.

Builds on

47 of 57 references.

References · 47

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  5. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  6. 2018Demystifying MMD GANscited by 1,293
  7. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  8. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  9. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  10. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 695
  11. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  12. 2020GANSpace: Discovering Interpretable GAN Controlscited by 614
35 more
  1. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 544
  2. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  3. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  4. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 332
  5. 2017Data Augmentation Generative Adversarial Networkscited by 278
  6. 2020StyleRig: Rigging StyleGAN for 3D Control over Portrait Imagescited by 268
  7. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 207
  8. 2019GANalyze: Toward Visual Definitions of Cognitive Image Propertiescited by 193
  9. 2020Editing in Style: Uncovering the Local Semantics of GANscited by 183
  10. 2018Transferring GANs: generating images from limited datacited by 134
  11. 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
  12. 2020Few-shot Image Generation with Elastic Weight Consolidationcited by 122
  13. 2019MineGAN: effective knowledge transfer from GANs to target domains with few imagescited by 106
  14. 2019Image Generation From Small Datasets via Batch Statistics Adaptationcited by 102
  15. 2021Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networkscited by 68
  16. 2023Few-Shot Defect Image Generation via Defect-Aware Feature Manipulationcited by 67
  17. 2022Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfercited by 66
  18. 2020Few-Shot Adaptation of Generative Adversarial Networkscited by 64
  19. 2022Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignmentcited by 54
  20. 2021JoJoGAN: One Shot Face Stylizationcited by 49
  21. 2022A Closer Look at Few-shot Image Generationcited by 49
  22. 2021Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Expertscited by 46
  23. 2021Image-Based CLIP-Guided Essence Transfercited by 39
  24. 2022Few-Shot Font Generation by Learning Fine-Grained Local Stylescited by 34
  25. 2022Few-shot Image Generation via Adaptation-Aware Kernel Modulationcited by 33
  26. 2022One-Shot Adaptation of GAN in Just One CLIPcited by 31
  27. 2020F2GAN: Fusing-and-Filling GAN for Few-shot Image Generationcited by 29
  28. 2022Finding Directions in GAN's Latent Space for Neural Face Reenactmentcited by 27
  29. 2020MatchingGAN: Matching-based Few-shot Image Generationcited by 26
  30. 2022Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networkscited by 23
  31. 2020DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Deltacited by 22
  32. 2022A Comprehensive Survey on Data-Efficient GANs in Image Generationcited by 20
  33. 2022Generalized One-shot Domain Adaptation of Generative Adversarial Networkscited by 19
  34. 2022Attribute Group Editing for Reliable Few-shot Image Generationcited by 15
  35. 2020Style Intervention: How to Achieve Spatial Disentanglement with Style-based Generators?cited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 7; 2025: 2; 2026: 1.

12 papers.

  1. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
  2. 2024Transfer Learning for Diffusion Modelscited by 10
  3. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  4. 2024CFTS-GAN: Continual Few-Shot Teacher Student for Generative Adversarial Networkscited by 4
  5. 2024GCA-3D: Towards Generalized and Consistent Domain Adaptation of 3D Generatorscited by 4
  6. 2025Few-shot Implicit Function Generation via Equivariancecited by 2
  7. 2026Autoregression-Free Neural Operators for Time-Dependent PDEscited by 2
  8. 2024Few-shot Image Generation via Information Transfer from the Built Geodesic Surfacecited by 1
  9. 2024DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuningcited by 1
  10. 2024UniHDA: A Unified and Versatile Framework for Multi-Modal Hybrid Domain Adaptationcited by 0
  11. 2024Conditional Diffusion on Web-Scale Image Pairs leads to Diverse Image Variationscited by 0
  12. 2025A Turn Toward Better Alignment: Few-Shot Generative Adaptation with Equivariant Feature Rotationcited by 0