mlsanityData to 7 Oct 2026

Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment

arXiv 2203.04121 ↗First posted 6 Mar 2022cs.CVcited by 54

Not on the map. Why?

Abstract (arXiv)

Training a generative adversarial network (GAN) with limited data has been a challenging task. A feasible solution is to start with a GAN well-trained on a large scale source domain and adapt it to the target domain with a few samples, termed as few shot generative model adaption. However, existing methods are prone to model overfitting and collapse in extremely few shot setting (less than 10). To solve this problem, we propose a relaxed spatial structural alignment method to calibrate the target generative models during the adaption. We design a cross-domain spatial structural consistency loss comprising the self-correlation and disturbance correlation consistency loss. It helps align the spatial structural information between the synthesis image pairs of the source and target domains. To relax the cross-domain alignment, we compress the original latent space of generative models to a subspace. Image pairs generated from the subspace are pulled closer. Qualitative and quantitative experiments show that our method consistently surpasses the state-of-the-art methods in few shot setting.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 31 of its 42 references that are in the map. First posted on arXiv 6 Mar 2022.

Builds on

31 of 42 references.

References · 31

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2016Improved Techniques for Training GANscited by 2,938
  5. 2015Fast R-CNNcited by 2,930
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  8. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  9. 2015Holistically-Nested Edge Detectioncited by 590
  10. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  11. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  12. 2018Diverse Image-to-Image Translation via Disentangled Representationscited by 296
19 more
  1. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  2. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 206
  3. 2016Semantic Image Inpainting with Deep Generative Modelscited by 156
  4. 2018Transferring GANs: generating images from limited datacited by 134
  5. 2019Consistency Regularization for Generative Adversarial Networkscited by 134
  6. 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
  7. 2020Few-shot Image Generation with Elastic Weight Consolidationcited by 122
  8. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  9. 2019MineGAN: effective knowledge transfer from GANs to target domains with few imagescited by 106
  10. 2019Image Generation From Small Datasets via Batch Statistics Adaptationcited by 102
  11. 2020Image Augmentations for GAN Trainingcited by 78
  12. 2020Few-Shot Adaptation of Generative Adversarial Networkscited by 64
  13. 2019FIGR: Few-shot Image Generation with Reptilecited by 54
  14. 2018Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistencycited by 41
  15. 2020COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encodercited by 39
  16. 2021Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognitioncited by 39
  17. 2020DAWSON: A Domain Adaptive Few Shot Generation Frameworkcited by 27
  18. 2020Semi-supervised Learning for Few-shot Image-to-Image Translationcited by 25
  19. 2020TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Imagescited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 22; 2024: 19; 2025: 5; 2026: 2.

54 papers.

Sort:

By area:

  1. 2023Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Modelscited by 297
  2. 2022A Closer Look at Few-shot Image Generationcited by 49
  3. 2022One-Shot Adaptation of GAN in Just One CLIPcited by 31
  4. 2023Zero-shot Generative Model Adaptation via Image-specific Prompt Learningcited by 27
  5. 2022Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networkscited by 23
  6. 2022Few-shot Image Generation with Diffusion Modelscited by 21
  7. 2024StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbingcited by 20
  8. 2022Generalized One-shot Domain Adaptation of Generative Adversarial Networkscited by 19
  9. 2023Exploring Incompatible Knowledge Transfer in Few-shot Image Generationcited 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. 2023DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Datacited by 15
38 more
  1. 2023Scenimefy: Learning to Craft Anime Scene via Semi-Supervised Image-to-Image Translationcited by 15
  2. 2024Deformable One-shot Face Stylization via DINO Semantic Guidancecited by 14
  3. 2022Few-shot Image Generation via Masked Discriminationcited by 12
  4. 2023WeditGAN: Few-Shot Image Generation via Latent Space Relocationcited by 12
  5. 2023LFS-GAN: Lifelong Few-Shot Image Generationcited by 11
  6. 2023Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaptioncited by 11
  7. 2023Adapt then Unlearn: Exploring Parameter Space Semantics for Unlearning in Generative Adversarial Networkscited by 11
  8. 2023Learning to Evaluate the Artness of AI-generated Imagescited by 10
  9. 2024Transfer Learning for Diffusion Modelscited by 10
  10. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  11. 2024Pick-and-Draw: Training-free Semantic Guidance for Text-to-Image Personalizationcited by 9
  12. 2024Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Surveycited by 9
  13. 2024Few-Shot Image Generation by Conditional Relaxing Diffusion Inversioncited by 7
  14. 2023One-for-All: Towards Universal Domain Translation with a Single StyleGANcited by 6
  15. 2023Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generationcited by 5
  16. 2025Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigationcited by 5
  17. 2024Stylized Face Sketch Extraction via Generative Prior with Limited Datacited by 4
  18. 2024LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Examplecited by 4
  19. 2024CFTS-GAN: Continual Few-Shot Teacher Student for Generative Adversarial Networkscited by 4
  20. 2024GCA-3D: Towards Generalized and Consistent Domain Adaptation of 3D Generatorscited by 4
  21. 2023Smoothness Similarity Regularization for Few-Shot GAN Adaptationcited by 3
  22. 2024Towards Robustness and Diversity: Continual Learning in Dialog Generation with Text-Mixup and Batch Nuclear-Norm Maximizationcited by 3
  23. 2024One-shot Generative Domain Adaptation in 3D GANscited by 3
  24. 2023Few-shot Hybrid Domain Adaptation of Image Generatorscited by 2
  25. 2025Few-shot Implicit Function Generation via Equivariancecited by 2
  26. 2023Few-shot 3D Shape Generationcited by 1
  27. 2023AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulationcited by 1
  28. 2023Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variationscited by 1
  29. 2023Few-shot Image Generation via Style Adaptation and Content Preservationcited by 1
  30. 2024Few-shot Image Generation via Information Transfer from the Built Geodesic Surfacecited by 1
  31. 2024Selective Test-Time Adaptation for Unsupervised Anomaly Detection using Neural Implicit Representationscited by 1
  32. 2024DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuningcited by 1
  33. 2024HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulationcited by 1
  34. 2025Generative Adversarial Networks with Limited Data: A Survey and Benchmarkingcited by 1
  35. 2025CoLoR-GAN: Continual Few-Shot Learning with Low-Rank Adaptation in Generative Adversarial Networkscited by 1
  36. 2023Few-shot Face Image Translation via GAN Prior Distillationcited by 0
  37. 2024UniHDA: A Unified and Versatile Framework for Multi-Modal Hybrid Domain Adaptationcited by 0
  38. 2024Conditional Diffusion on Web-Scale Image Pairs leads to Diverse Image Variationscited by 0

50 most cited of 54 All 54 (JSON)