mlsanityData to 7 Oct 2026

Regularizing Generative Adversarial Networks under Limited Data

arXiv 2104.03310 ↗First posted 7 Apr 2021cs.LG cs.CVcited by 105

Not on the map. Why?

Abstract (arXiv)

Recent years have witnessed the rapid progress of generative adversarial networks (GANs). However, the success of the GAN models hinges on a large amount of training data. This work proposes a regularization approach for training robust GAN models on limited data. We theoretically show a connection between the regularized loss and an f-divergence called LeCam-divergence, which we find is more robust under limited training data. Extensive experiments on several benchmark datasets demonstrate that the proposed regularization scheme 1) improves the generalization performance and stabilizes the learning dynamics of GAN models under limited training data, and 2) complements the recent data augmentation methods. These properties facilitate training GAN models to achieve state-of-the-art performance when only limited training data of the ImageNet benchmark is available.

Key facts. Cited by 105 papers in the map (data through 7 Oct 2026). Builds on 67 of its 88 references that are in the map. First posted on arXiv 7 Apr 2021.

Builds on

67 of 88 references.

References · 67

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2016Improved Techniques for Training GANscited by 2,938
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2017Improved Training of Wasserstein GANscited by 2,223
  7. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  8. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  9. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  10. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  11. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  12. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
38 more
  1. 2016Least Squares Generative Adversarial Networkscited by 1,000
  2. 2017A Closer Look at Memorization in Deep Networkscited by 936
  3. 2018Self-Attention Generative Adversarial Networkscited by 809
  4. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  5. 2018Which Training Methods for GANs do actually Converge?cited by 672
  6. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  7. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  8. 2017Wasserstein GANcited by 635
  9. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  10. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  11. 2019Confident Learning: Estimating Uncertainty in Dataset Labelscited by 411
  12. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  13. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  14. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  15. 2018GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classificationcited by 242
  16. 2018The relativistic discriminator: a key element missing from standard GANcited by 234
  17. 2017Geometric GANcited by 232
  18. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
  19. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  20. 2020Semantic Photo Manipulation with a Generative Image Priorcited by 178
  21. 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
  22. 2018Synthetic Data Augmentation using GAN for Improved Liver Lesion Classificationcited by 136
  23. 2018Transferring GANs: generating images from limited datacited by 134
  24. 2019Progressive Domain Adaptation for Object Detectioncited by 134
  25. 2019Consistency Regularization for Generative Adversarial Networkscited by 134
  26. 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
  27. 2016Mode Regularized Generative Adversarial Networkscited by 123
  28. 2017BEGAN: Boundary Equilibrium Generative Adversarial Networkscited by 121
  29. 2016Energy-based Generative Adversarial Networkcited by 119
  30. 2017Stabilizing Training of Generative Adversarial Networks through Regularizationcited by 118
  31. 2019MineGAN: effective knowledge transfer from GANs to target domains with few imagescited by 106
  32. 2017The Numerics of GANscited by 104
  33. 2019Image Generation From Small Datasets via Batch Statistics Adaptationcited by 102
  34. 2020Image Augmentations for GAN Trainingcited by 78
  35. 2019Diversity-Sensitive Conditional Generative Adversarial Networkscited by 77
  36. 2020Transforming and Projecting Images into Class-conditional Generative Networkscited by 76
  37. 2016Amortised MAP Inference for Image Super-resolutioncited by 68
  38. 2020Improved Consistency Regularization for GANscited by 67

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 27; 2023: 28; 2024: 14; 2025: 12; 2026: 16.

105 papers.

Sort:

By area:

  1. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  2. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 633
  3. 2022Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priorscited by 487
  4. 2022MAGVIT: Masked Generative Video Transformercited by 341
  5. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  6. 2024Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generationcited by 153
  7. 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Modelscited by 131
  8. 2021ViTGAN: Training GANs with Vision Transformerscited by 110
  9. 2024MaskBit: Embedding-free Image Generation via Bit Tokenscited by 96
  10. 2024ImageFolder: Autoregressive Image Generation with Folded Tokenscited by 93
  11. 2025Masked Autoencoders Are Effective Tokenizers for Diffusion Modelscited by 93
  12. 2025Seaweed-7B: Cost-Effective Training of Video Generation Foundation Modelcited by 81
38 more
  1. 2022Visual Prompt Tuning for Generative Transfer Learningcited by 75
  2. 2024SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizercited by 55
  3. 2023SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMscited by 54
  4. 2021Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Datacited by 53
  5. 2022A Closer Look at Few-shot Image Generationcited by 49
  6. 2025Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokenscited by 48
  7. 2023Class-Balancing Diffusion Modelscited by 47
  8. 2024LARP: Tokenizing Videos with a Learned Autoregressive Generative Priorcited by 46
  9. 2024Scalable Image Tokenization with Index Backpropagation Quantizationcited by 44
  10. 2023Deep Momentum Multi-Marginal Schr"odinger Bridgecited by 40
  11. 2022StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesiscited by 38
  12. 2024Language-Guided Image Tokenization for Generationcited by 36
  13. 2022Diffusion Guided Domain Adaptation of Image Generatorscited by 35
  14. 2025Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenizationcited by 35
  15. 2022Few-shot Image Generation via Adaptation-Aware Kernel Modulationcited by 33
  16. 2022DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Modelcited by 32
  17. 2022Rewriting Geometric Rules of a GANcited by 25
  18. 2022Collapse by Conditioning: Training Class-conditional GANs with Limited Datacited by 24
  19. 2022WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generationcited by 22
  20. 2023MapPrior: Bird's-Eye View Map Layout Estimation with Generative Modelscited by 21
  21. 2022A Comprehensive Survey on Data-Efficient GANs in Image Generationcited by 20
  22. 2022HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networkscited by 19
  23. 2023Exploring Incompatible Knowledge Transfer in Few-shot Image Generationcited by 19
  24. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
  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. 2021Few-shot Image Generation with Mixup-based Distance Learningcited by 16
  28. 2022FreGAN: Exploiting Frequency Components for Training GANs under Limited Datacited by 16
  29. 2023KD-DLGAN: Data Limited Image Generation via Knowledge Distillationcited by 16
  30. 2023EGC: Image Generation and Classification via a Diffusion Energy-Based Modelcited by 16
  31. 2021GenCo: Generative Co-training for Generative Adversarial Networks with Limited Datacited by 14
  32. 2021Manifold Learning Benefits GANscited by 14
  33. 2022Improving GANs for Long-Tailed Data through Group Spectral Regularizationcited by 14
  34. 2023NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANscited by 12
  35. 2024XQ-GAN: An Open-source Image Tokenization Framework for Autoregressive Generationcited by 12
  36. 2025Dyn-O: Building Structured World Models with Object-Centric Representationscited by 12
  37. 2022StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptationcited by 10
  38. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9

50 most cited of 105 All 105 (JSON)