mlsanityData to 7 Oct 2026

Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective

arXiv 2103.00397 ↗First posted 28 Feb 2021cs.LG cs.AI cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

Training generative adversarial networks (GANs) with limited real image data generally results in deteriorated performance and collapsed models. To conquer this challenge, we are inspired by the latest observation, that one can discover independently trainable and highly sparse subnetworks (a.k.a., lottery tickets) from GANs. Treating this as an inductive prior, we suggest a brand-new angle towards data-efficient GAN training: by first identifying the lottery ticket from the original GAN using the small training set of real images; and then focusing on training that sparse subnetwork by re-using the same set. We find our coordinated framework to offer orthogonal gains to existing real image data augmentation methods, and we additionally present a new feature-level augmentation that can be applied together with them. Comprehensive experiments endorse the effectiveness of our proposed framework, across various GAN architectures (SNGAN, BigGAN, and StyleGAN-V2) and diverse datasets (CIFAR-10, CIFAR-100, Tiny-ImageNet, ImageNet, and multiple few-shot generation datasets). Codes are available at: https://github.com/VITA-Group/Ultra-Data-Efficient-GAN-Training.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 81 of its 105 references that are in the map. First posted on arXiv 28 Feb 2021.

Builds on

81 of 105 references.

References · 81

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2016Improved Techniques for Training GANscited by 2,938
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  9. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  10. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  11. 2017Improved Training of Wasserstein GANscited by 2,223
  12. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
38 more
  1. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  2. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  3. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  4. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  5. 2016Adversarial Machine Learning at Scalecited by 934
  6. 2018Robustness May Be at Odds with Accuracycited by 873
  7. 2018Self-Attention Generative Adversarial Networkscited by 809
  8. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  9. 2018Which Training Methods for GANs do actually Converge?cited by 672
  10. 2019Linear Mode Connectivity and the Lottery Ticket Hypothesiscited by 627
  11. 2018Rethinking the Value of Network Pruningcited by 595
  12. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  13. 2019The State of Sparsity in Deep Neural Networkscited by 471
  14. 2020Picking Winning Tickets Before Training by Preserving Gradient Flowcited by 467
  15. 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
  16. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  17. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
  18. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  19. 2020Large-Scale Adversarial Training for Vision-and-Language Representation Learningcited by 327
  20. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  21. 2018Adversarially Robust Generalization Requires More Datacited by 318
  22. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
  23. 2019Adversarial Examples Improve Image Recognitioncited by 283
  24. 2017Data Augmentation Generative Adversarial Networkscited by 278
  25. 2020The Lottery Ticket Hypothesis for Pre-trained BERT Networkscited by 275
  26. 2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 261
  27. 2018cGANs with Projection Discriminatorcited by 253
  28. 2017MMD GAN: Towards Deeper Understanding of Moment Matching Networkcited by 251
  29. 2020Comparing Rewinding and Fine-tuning in Neural Network Pruningcited by 238
  30. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  31. 2020A Review on Generative Adversarial Networks: Algorithms, Theory, and Applicationscited by 209
  32. 2018Disentangling Adversarial Robustness and Generalizationcited by 171
  33. 2019Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networkscited by 160
  34. 2020Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuningcited by 152
  35. 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
  36. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  37. 2018Transferring GANs: generating images from limited datacited by 134
  38. 2019Consistency Regularization for Generative Adversarial Networkscited by 134

50 most cited of 81 All 81 (JSON)

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 9; 2023: 8; 2024: 5; 2025: 2.

25 papers.

Sort:

By area:

  1. 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Modelscited by 131
  2. 2023On Efficient Training of Large-Scale Deep Learning Models: A Literature Reviewcited by 26
  3. 2023Ten Lessons We Have Learned in the New "Sparseland": A Short Handbook for Sparse Neural Network Researcherscited by 25
  4. 2023Rethinking Graph Lottery Tickets: Graph Sparsity Matterscited by 23
  5. 2024A Survey of Lottery Ticket Hypothesiscited by 23
  6. 2022Most Activation Functions Can Win the Lottery Without Excessive Depthcited by 21
  7. 2022A Comprehensive Survey on Data-Efficient GANs in Image Generationcited by 20
  8. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
  9. 2022FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANscited by 17
  10. 2022Convolutional and Residual Networks Provably Contain Lottery Ticketscited by 16
  11. 2024ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learningcited by 10
  12. 2022On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networkscited by 9
13 more
  1. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  2. 2021Generating Novel Scene Compositions from Single Images and Videoscited by 8
  3. 2023Balanced Training for Sparse GANscited by 8
  4. 2022Augmentation-Aware Self-Supervision for Data-Efficient GAN Trainingcited by 7
  5. 2022DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Datacited by 7
  6. 2022Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANscited by 5
  7. 2022Anomaly Detection in Additive Manufacturing Processes using Supervised Classification with Imbalanced Sensor Data based on Generative Adversarial Networkcited by 5
  8. 2024CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalizationcited by 2
  9. 20233D GANs and Latent Space: A comprehensive surveycited by 1
  10. 2025Stepsize anything: A unified learning rate schedule for budgeted-iteration trainingcited by 1
  11. 2024Chasing Better Deep Image Priors between Over- and Under-parameterizationcited by 0
  12. 2024Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural Networkscited by 0
  13. 2025Enhancing Drug Discovery: Autoencoder-Based Latent Space Augmentation for Improved Molecular Solubility Prediction using LatMixSolcited by 0