mlsanityData to 14 Oct 2026

A Comprehensive Survey on Data-Efficient GANs in Image Generation

arXiv 2204.08329 ↗First posted 18 Apr 2022cs.CV cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

Generative Adversarial Networks (GANs) have achieved remarkable achievements in image synthesis. These successes of GANs rely on large scale datasets, requiring too much cost. With limited training data, how to stable the training process of GANs and generate realistic images have attracted more attention. The challenges of Data-Efficient GANs (DE-GANs) mainly arise from three aspects: (i) Mismatch Between Training and Target Distributions, (ii) Overfitting of the Discriminator, and (iii) Imbalance Between Latent and Data Spaces. Although many augmentation and pre-training strategies have been proposed to alleviate these issues, there lacks a systematic survey to summarize the properties, challenges, and solutions of DE-GANs. In this paper, we revisit and define DE-GANs from the perspective of distribution optimization. We conclude and analyze the challenges of DE-GANs. Meanwhile, we propose a taxonomy, which classifies the existing methods into three categories: Data Selection, GANs Optimization, and Knowledge Sharing. Last but not the least, we attempt to highlight the current problems and the future directions.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 49 of its 73 references that are in the map. First posted on arXiv 18 Apr 2022.

Builds on

49 of 73 references.

References · 49

  1. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  6. 2017Improved Training of Wasserstein GANscited by 2,235
  7. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  8. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 695
  9. 2018An Empirical Study of Example Forgetting during Deep Neural Network Learningcited by 678
  10. 2020Overfitting in adversarially robust deep learningcited by 506
  11. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
  12. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
37 more
  1. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  2. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  3. 2018Not All Samples Are Created Equal: Deep Learning with Importance Samplingcited by 328
  4. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 213
  5. 2020A Review on Generative Adversarial Networks: Algorithms, Theory, and Applicationscited by 209
  6. 2021Projected GANs Converge Fastercited by 208
  7. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 207
  8. 2021Data Augmentation Can Improve Robustnesscited by 194
  9. 2019MirrorGAN: Learning Text-to-image Generation by Redescriptioncited by 176
  10. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  11. 2018Transferring GANs: generating images from limited datacited by 134
  12. 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
  13. 2020Few-shot Image Generation with Elastic Weight Consolidationcited by 122
  14. 2021Regularizing Generative Adversarial Networks under Limited Datacited by 107
  15. 2019MineGAN: effective knowledge transfer from GANs to target domains with few imagescited by 106
  16. 2019Image Generation From Small Datasets via Batch Statistics Adaptationcited by 102
  17. 2020A Survey on Generative Adversarial Networks: Variants, Applications, and Trainingcited by 97
  18. 2021Ensembling Off-the-shelf Models for GAN Trainingcited by 86
  19. 2020Improved Techniques for Training Single-Image GANscited by 78
  20. 2020Image Augmentations for GAN Trainingcited by 78
  21. 2020Few-Shot Adaptation of Generative Adversarial Networkscited by 64
  22. 2021Data-Efficient Instance Generation from Instance Discriminationcited by 58
  23. 2019FIGR: Few-shot Image Generation with Reptilecited by 56
  24. 2021Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Datacited by 53
  25. 2021Efficient Lottery Ticket Finding: Less Data is Morecited by 44
  26. 2017Perceptual Adversarial Networks for Image-to-Image Transformationcited by 42
  27. 2018Evolutionary Generative Adversarial Networkscited by 42
  28. 2021One-Shot Generative Domain Adaptationcited by 41
  29. 2020F2GAN: Fusing-and-Filling GAN for Few-shot Image Generationcited by 29
  30. 2020A Systematic Survey of Regularization and Normalization in GANscited by 27
  31. 2021Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspectivecited by 25
  32. 2022Collapse by Conditioning: Training Class-conditional GANs with Limited Datacited by 25
  33. 2020Instance Selection for GANscited by 23
  34. 2022When, Why, and Which Pretrained GANs Are Useful?cited by 14
  35. 2020AE-OT-GAN: Training GANs from data specific latent distributioncited by 13
  36. 2020Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencodercited by 13
  37. 2020Data InStance Prior (DISP) in Generative Adversarial Networkscited by 7

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 8; 2024: 4; 2025: 4.

20 papers.

Sort:

  1. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
  2. 2023Domain Re-Modulation for Few-Shot Generative Domain Adaptationcited by 18
  3. 2022FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANscited by 17
  4. 2022Data-Efficient Backdoor Attackscited by 13
  5. 2023WeditGAN: Few-Shot Image Generation via Latent Space Relocationcited by 12
  6. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  7. 2025Pedestrian Trajectory Prediction Based on Social Interactions Learning With Random Weightscited by 8
  8. 2023Explore the Effect of Data Selection on Poison Efficiency in Backdoor Attackscited by 7
  9. 2023Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generationcited by 5
  10. 2022Leveraging GAN Priors for Few-Shot Part Segmentationcited by 4
  11. 2022Deep Generative Modeling on Limited Data with Regularization by Nontransferable Pre-trained Modelscited by 4
  12. 2024Discriminative Hamiltonian Variational Autoencoder for Accurate Tumor Segmentation in Data-Scarce Regimescited by 3
8 more
  1. 2024Seizing the Means of Production: Exploring the Landscape of Crafting, Adapting and Navigating Generative AI Models in the Visual Artscited by 2
  2. 2023Advancing Perception in Artificial Intelligence through Principles of Cognitive Sciencecited by 1
  3. 2023Improving Few-shot Image Generation by Structural Discrimination and Textural Modulationcited by 0
  4. 2024Parameter and Data-Efficient Spectral StyleDCGANcited by 0
  5. 2024NODE-AdvGAN: Improving the transferability and perceptual similarity of adversarial examples by dynamic-system-driven adversarial generative modelcited by 0
  6. 2025A Comprehensive Survey on Image Signal Processing Approaches for Low-Illumination Image Enhancementcited by 0
  7. 2025Unified Kernel-Segregated Transpose Convolution Operationcited by 0
  8. 2025Prime Convolutional Model: Breaking the Ground for Theoretical Explainabilitycited by 0