mlsanityData to 14 Oct 2026

GenLabel: Mixup Relabeling using Generative Models

arXiv 2201.02354 ↗First posted 7 Jan 2022cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Mixup is a data augmentation method that generates new data points by mixing a pair of input data. While mixup generally improves the prediction performance, it sometimes degrades the performance. In this paper, we first identify the main causes of this phenomenon by theoretically and empirically analyzing the mixup algorithm. To resolve this, we propose GenLabel, a simple yet effective relabeling algorithm designed for mixup. In particular, GenLabel helps the mixup algorithm correctly label mixup samples by learning the class-conditional data distribution using generative models. Via extensive theoretical and empirical analysis, we show that mixup, when used together with GenLabel, can effectively resolve the aforementioned phenomenon, improving the generalization performance and the adversarial robustness.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 51 of its 69 references that are in the map. First posted on arXiv 7 Jan 2022.

Builds on

51 of 69 references.

References · 51

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  10. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  11. 2021Variational Diffusion Modelscited by 1,153
  12. 2019An Introduction to Variational Autoencoderscited by 1,000
38 more
  1. 2016Adversarial Machine Learning at Scalecited by 936
  2. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  3. 2017The Implicit Bias of Gradient Descent on Separable Datacited by 655
  4. 2014OpenML: networked science in machine learningcited by 526
  5. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  6. 2019On Evaluating Adversarial Robustnesscited by 447
  7. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  8. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 370
  9. 2021GAN Inversion: A Surveycited by 367
  10. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  11. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
  12. 2016Adversarial Feature Learningcited by 350
  13. 2017Data Augmentation Generative Adversarial Networkscited by 278
  14. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 261
  15. 2018Adversarial Attacks and Defences: A Surveycited by 259
  16. 2018Generating Adversarial Examples with Adversarial Networkscited by 258
  17. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
  18. 2016Adversarially Learned Inferencecited by 216
  19. 2020How Does Mixup Help With Robustness and Generalization?cited by 193
  20. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  21. 2018MixUp as Locally Linear Out-Of-Manifold Regularizationcited by 158
  22. 2020SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularizationcited by 149
  23. 2016Inverting The Generator Of A Generative Adversarial Networkcited by 140
  24. 2021Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversitycited by 128
  25. 2018Towards the first adversarially robust neural network model on MNISTcited by 104
  26. 2018Data Augmentation by Pairing Samples for Images Classificationcited by 96
  27. 2020On Mixup Regularizationcited by 83
  28. 2019OpenML-Python: an extensible Python API for OpenMLcited by 63
  29. 2019Data Augmentation Using GANscited by 58
  30. 2017Learning from Between-class Examples for Deep Sound Recognitioncited by 54
  31. 2021Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Datacited by 45
  32. 2018Are Generative Classifiers More Robust to Adversarial Attacks?cited by 36
  33. 2017The Robust Manifold Defense: Adversarial Training using Generative Modelscited by 35
  34. 2019Imperceptible Adversarial Attacks on Tabular Datacited by 35
  35. 2018Resisting Adversarial Attacks using Gaussian Mixture Variational Autoencoderscited by 26
  36. 2021Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixingcited by 15
  37. 2021k-Mixup Regularization for Deep Learning via Optimal Transportcited by 14
  38. 2019Linear and Quadratic Discriminant Analysis: Tutorialcited by 11

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 1; 2024: 3; 2025: 1.

10 papers.

  1. 2022LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Taskscited by 148
  2. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 31
  3. 2022A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspectivecited by 27
  4. 2024A Survey on Mixup Augmentations and Beyondcited by 20
  5. 2023Over-training with Mixup May Hurt Generalizationcited by 13
  6. 2022Human-in-the-Loop Mixupcited by 8
  7. 2024IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighborscited by 4
  8. 2025A Generalized Theory of Mixup for Structure-Preserving Synthetic Datacited by 2
  9. 2022Recovering Top-Two Answers and Confusion Probability in Multi-Choice Crowdsourcingcited by 0
  10. 2024Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognitioncited by 0