mlsanityData to 7 Oct 2026

Tailoring Mixup to Data for Calibration

arXiv 2311.01434 ↗First posted 2 Nov 2023cs.LG cs.AI stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

Among all data augmentation techniques proposed so far, linear interpolation of training samples, also called Mixup, has found to be effective for a large panel of applications. Along with improved predictive performance, Mixup is also a good technique for improving calibration. However, mixing data carelessly can lead to manifold mismatch, i.e., synthetic data lying outside original class manifolds, which can deteriorate calibration. In this work, we show that the likelihood of assigning a wrong label with mixup increases with the distance between data to mix. To this end, we propose to dynamically change the underlying distributions of interpolation coefficients depending on the similarity between samples to mix, and define a flexible framework to do so without losing in diversity. We provide extensive experiments for classification and regression tasks, showing that our proposed method improves predictive performance and calibration of models, while being much more efficient.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 58 of its 87 references that are in the map. First posted on arXiv 2 Nov 2023.

Builds on

58 of 87 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2017On Calibration of Modern Neural Networkscited by 4,860
  7. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  8. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  10. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  11. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  12. 2019Natural Adversarial Examplescited by 1,401
38 more
  1. 2019When Does Label Smoothing Help?cited by 985
  2. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  3. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
  4. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
  5. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  6. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  7. 2020Calibrating Deep Neural Networks using Focal Losscited by 353
  8. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  9. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 260
  10. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 208
  11. 2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
  12. 2018MixUp as Locally Linear Out-Of-Manifold Regularizationcited by 158
  13. 2020Remix: Rebalanced Mixupcited by 144
  14. 2020Confidence-Aware Learning for Deep Neural Networkscited by 113
  15. 2018Data Augmentation by Pairing Samples for Images Classificationcited by 96
  16. 2021The Devil is in the Margin: Margin-based Label Smoothing for Network Calibrationcited by 91
  17. 2019Distribution Calibration for Regressioncited by 88
  18. 2018Data Augmentation using Random Image Cropping and Patching for Deep CNNscited by 87
  19. 2019Evaluating and Calibrating Uncertainty Prediction in Regression Taskscited by 85
  20. 2021AutoMix: Unveiling the Power of Mixup for Stronger Classifierscited by 69
  21. 2014Input Warping for Bayesian Optimization of Non-stationary Functionscited by 66
  22. 2021DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Datacited by 62
  23. 2021When and How Mixup Improves Calibrationcited by 59
  24. 2022C-Mixup: Improving Generalization in Regressioncited by 57
  25. 2017Between-class Learning for Image Classificationcited by 50
  26. 2022Packed-Ensembles for Efficient Uncertainty Estimationcited by 49
  27. 2020Combining Ensembles and Data Augmentation can Harm your Calibrationcited by 44
  28. 2018Improved Mixed-Example Data Augmentationcited by 42
  29. 2021MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognitioncited by 38
  30. 2021AlignMixup: Improving Representations By Interpolating Aligned Featurescited by 33
  31. 2021MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworkscited by 32
  32. 2022SelecMix: Debiased Learning by Contradicting-pair Samplingcited by 29
  33. 2021Noisy Feature Mixupcited by 27
  34. 2022RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustnesscited by 27
  35. 2022OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learningcited by 21
  36. 2021Robust Semantic Segmentation with Superpixel-Mixcited by 19
  37. 2021Towards Understanding the Data Dependency of Mixup-style Trainingcited by 19
  38. 2023RankMixup: Ranking-Based Mixup Training for Network Calibrationcited by 19

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 3.

5 papers.

  1. 2024A Survey on Mixup Augmentations and Beyondcited by 18
  2. 2025Improving Mixup Calibration with Wasserstein Distributionally Robust Optimizationcited by 1
  3. 2026Evolution-Inspired Sample Competition for Deep Neural Network Optimizationcited by 0
  4. 2026Inducing Artificial Uncertainty in Language Modelscited by 0
  5. 2026An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibrationcited by 0