mlsanityData to 7 Oct 2026

Transferring GANs: generating images from limited data

arXiv 1805.01677 ↗First posted 4 May 2018cs.CVcited by 134

Not on the map. Why?

Abstract (arXiv)

Transferring the knowledge of pretrained networks to new domains by means of finetuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the context of generative deep networks. Therefore, we study domain adaptation applied to image generation with generative adversarial networks. We evaluate several aspects of domain adaptation, including the impact of target domain size, the relative distance between source and target domain, and the initialization of conditional GANs. Our results show that using knowledge from pretrained networks can shorten the convergence time and can significantly improve the quality of the generated images, especially when the target data is limited. We show that these conclusions can also be drawn for conditional GANs even when the pretrained model was trained without conditioning. Our results also suggest that density may be more important than diversity and a dataset with one or few densely sampled classes may be a better source model than more diverse datasets such as ImageNet or Places.

Key facts. Cited by 134 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 32; 2022: 41; 2023: 36; 2024: 14; 2025: 3; 2026: 8.

134 papers.

Sort:

By area:

  1. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  2. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,099
  3. 2023Ablating Concepts in Text-to-Image Diffusion Modelscited by 312
  4. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 206
  5. 2021Projected GANs Converge Fastercited by 204
  6. 2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
  7. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  8. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  9. 2021Regularizing Generative Adversarial Networks under Limited Datacited by 105
  10. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  11. 2022Generative Neural Articulated Radiance Fieldscited by 101
  12. 2021Ensembling Off-the-shelf Models for GAN Trainingcited by 84
38 more
  1. 2022Visual Prompt Tuning for Generative Transfer Learningcited by 75
  2. 2022Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignmentcited by 54
  3. 2022A Closer Look at Few-shot Image Generationcited by 49
  4. 2021StyleAlign: Analysis and Applications of Aligned StyleGAN Modelscited by 48
  5. 2022UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translationcited by 42
  6. 2021One-Shot Generative Domain Adaptationcited by 41
  7. 2021Sketch Your Own GANcited by 37
  8. 2021Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classificationcited by 35
  9. 2022Few-shot Image Generation via Adaptation-Aware Kernel Modulationcited by 33
  10. 2021Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Datacited by 31
  11. 2022One-Shot Adaptation of GAN in Just One CLIPcited by 31
  12. 2022Fair Generative Models via Transfer Learningcited by 27
  13. 2023Zero-shot Generative Model Adaptation via Image-specific Prompt Learningcited by 27
  14. 2021Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspectivecited by 25
  15. 2022Rewriting Geometric Rules of a GANcited by 25
  16. 2022Collapse by Conditioning: Training Class-conditional GANs with Limited Datacited by 24
  17. 2022Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networkscited by 23
  18. 2022Few-shot Image Generation with Diffusion Modelscited by 21
  19. 2022A Comprehensive Survey on Data-Efficient GANs in Image Generationcited by 20
  20. 2022Generalized One-shot Domain Adaptation of Generative Adversarial Networkscited by 19
  21. 2022HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networkscited by 19
  22. 2023Exploring Incompatible Knowledge Transfer in Few-shot Image Generationcited by 19
  23. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
  24. 2021Paint4Poem: A Dataset for Artistic Visualization of Classical Chinese Poemscited by 18
  25. 2023Domain Re-Modulation for Few-Shot Generative Domain Adaptationcited by 18
  26. 2022FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANscited by 17
  27. 2023Unlearnable Examples Give a False Sense of Security: Piercing through Unexploitable Data with Learnable Examplescited by 17
  28. 2021Few-shot Image Generation with Mixup-based Distance Learningcited by 16
  29. 2022FreGAN: Exploiting Frequency Components for Training GANs under Limited Datacited by 16
  30. 2022DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domainscited by 15
  31. 2023DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Datacited by 15
  32. 2023Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translationcited by 15
  33. 2021GenCo: Generative Co-training for Generative Adversarial Networks with Limited Datacited by 14
  34. 2022When, Why, and Which Pretrained GANs Are Useful?cited by 14
  35. 2021Efficient Conditional GAN Transfer with Knowledge Propagation across Classescited by 13
  36. 2021Facial-Sketch Synthesis: A New Challengecited by 13
  37. 2022Few-shot Image Generation via Masked Discriminationcited by 12
  38. 2023WeditGAN: Few-Shot Image Generation via Latent Space Relocationcited by 12

50 most cited of 134 All 134 (JSON)