mlsanityData to 14 Oct 2026

Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis

arXiv 2101.04775 ↗First posted 12 Jan 2021cs.CV cs.AIcited by 140

Not on the map. Why?

Abstract (arXiv)

Training Generative Adversarial Networks (GAN) on high-fidelity images usually requires large-scale GPU-clusters and a vast number of training images. In this paper, we study the few-shot image synthesis task for GAN with minimum computing cost. We propose a light-weight GAN structure that gains superior quality on 1024*1024 resolution. Notably, the model converges from scratch with just a few hours of training on a single RTX-2080 GPU, and has a consistent performance, even with less than 100 training samples. Two technique designs constitute our work, a skip-layer channel-wise excitation module and a self-supervised discriminator trained as a feature-encoder. With thirteen datasets covering a wide variety of image domains (The datasets and code are available at: https://github.com/odegeasslbc/FastGAN-pytorch), we show our model's superior performance compared to the state-of-the-art StyleGAN2, when data and computing budget are limited.

Key facts. Cited by 140 papers in the map (data through 14 Oct 2026). Builds on 49 of its 61 references that are in the map. First posted on arXiv 12 Jan 2021.

Builds on

49 of 61 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2017Squeeze-and-Excitation Networkscited by 4,789
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  9. 2017Improved Training of Wasserstein GANscited by 2,235
  10. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  11. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  12. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
37 more
  1. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  2. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  3. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  4. 2016Language Modeling with Gated Convolutional Networkscited by 702
  5. 2018Which Training Methods for GANs do actually Converge?cited by 679
  6. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  7. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 657
  8. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 577
  9. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  10. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  11. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  12. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  13. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  14. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  15. 2017Geometric GANcited by 233
  16. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  17. 2019Scaling and Benchmarking Self-Supervised Visual Representation Learningcited by 201
  18. 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
  19. 2017BEGAN: Boundary Equilibrium Generative Adversarial Networkscited by 121
  20. 2016Energy-based Generative Adversarial Networkcited by 119
  21. 2019MineGAN: effective knowledge transfer from GANs to target domains with few imagescited by 106
  22. 2019Image Generation From Small Datasets via Batch Statistics Adaptationcited by 102
  23. 2017CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Normscited by 96
  24. 2018Self-Supervised GANs via Auxiliary Rotation Losscited by 94
  25. 2018The Unusual Effectiveness of Averaging in GAN Trainingcited by 73
  26. 2020Few-Shot Adaptation of Generative Adversarial Networkscited by 64
  27. 2016Stacked Generative Adversarial Networkscited by 44
  28. 2019Small-GAN: Speeding Up GAN Training Using Core-setscited by 41
  29. 2019Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Gamecited by 25
  30. 2019OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularizationcited by 17
  31. 2019MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networkscited by 14
  32. 2017Hierarchical Implicit Models and Likelihood-Free Variational Inferencecited by 13
  33. 2019Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesiscited by 11
  34. 2020Sketch-to-Art: Synthesizing Stylized Art Images From Sketchescited by 10
  35. 2020TIME: Text and Image Mutual-Translation Adversarial Networkscited by 9
  36. 2020Improving the Speed and Quality of GAN by Adversarial Trainingcited by 6
  37. 2019DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesiscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 25; 2022: 37; 2023: 37; 2024: 20; 2025: 10; 2026: 11.

140 papers.

Sort:

By area:

  1. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,106
  2. 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 532
  3. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
  4. 2023Improved Techniques for Training Consistency Modelscited by 439
  5. 2023Ablating Concepts in Text-to-Image Diffusion Modelscited by 317
  6. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  7. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 213
  8. 2021Projected GANs Converge Fastercited by 208
  9. 2022Diffusion-GAN: Training GANs with Diffusioncited by 205
  10. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  11. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  12. 2021Ensembling Off-the-shelf Models for GAN Trainingcited by 86
38 more
  1. 2023Differentially Private Diffusion Models Generate Useful Synthetic Imagescited by 86
  2. 2021Constrained Graphic Layout Generation via Latent Optimizationcited by 83
  3. 2021Large Scale Visual Food Recognitioncited by 75
  4. 2021Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codescited by 71
  5. 2021Aligning Latent and Image Spaces to Connect the Unconnectablecited by 70
  6. 2022MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-raycited by 66
  7. 2021SinGAN-Seg: Synthetic training data generation for medical image segmentationcited by 43
  8. 2022Federated Domain Generalization for Image Recognition via Cross-Client Style Transfercited by 40
  9. 2024Autoregressive Models in Vision: A Surveycited by 39
  10. 2022StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesiscited by 38
  11. 2022Diffusion Guided Domain Adaptation of Image Generatorscited by 35
  12. 2024The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipelinecited by 33
  13. 2021Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspectivecited by 25
  14. 2022Collapse by Conditioning: Training Class-conditional GANs with Limited Datacited by 25
  15. 2022Musika! Fast Infinite Waveform Music Generationcited by 24
  16. 2023Unifying GANs and Score-Based Diffusion as Generative Particle Modelscited by 21
  17. 2022A Comprehensive Survey on Data-Efficient GANs in Image Generationcited by 20
  18. 2022HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networkscited by 19
  19. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
  20. 2022FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANscited by 17
  21. 2021Few-shot Image Generation with Mixup-based Distance Learningcited by 16
  22. 2022A Style-aware Discriminator for Controllable Image Translationcited by 16
  23. 2022FreGAN: Exploiting Frequency Components for Training GANs under Limited Datacited by 16
  24. 2021Data synthesis and adversarial networks: A review and meta-analysis in cancer imagingcited by 15
  25. 2022LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designercited by 15
  26. 2022medigan: a Python library of pretrained generative models for medical image synthesiscited by 14
  27. 2022SinGRAF: Learning a 3D Generative Radiance Field for a Single Scenecited by 11
  28. 2023LFS-GAN: Lifelong Few-Shot Image Generationcited by 11
  29. 2023Emergence of Shape Bias in Convolutional Neural Networks through Activation Sparsitycited by 11
  30. 2025LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptationcited by 11
  31. 2021MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesiscited by 10
  32. 2022StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptationcited by 10
  33. 2022Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rulescited by 9
  34. 2023Conditional 360-degree Image Synthesis for Immersive Indoor Scene Decorationcited by 9
  35. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  36. 2024Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Surveycited by 9
  37. 2021Generating Novel Scene Compositions from Single Images and Videoscited by 8
  38. 2022Hierarchical Semantic Regularization of Latent Spaces in StyleGANscited by 8

50 most cited of 140 All 140 (JSON)