mlsanityData to 7 Oct 2026

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

arXiv 1912.02781 ↗First posted 5 Dec 2019stat.ML cs.CV cs.LGcited by 897

Not on the map. Why?

Cited by 31 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Modern deep neural networks can achieve high accuracy when the training distribution and test distribution are identically distributed, but this assumption is frequently violated in practice. When the train and test distributions are mismatched, accuracy can plummet. Currently there are few techniques that improve robustness to unforeseen data shifts encountered during deployment. In this work, we propose a technique to improve the robustness and uncertainty estimates of image classifiers. We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions. AugMix significantly improves robustness and uncertainty measures on challenging image classification benchmarks, closing the gap between previous methods and the best possible performance in some cases by more than half.

Key facts. Cited by 897 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 152; 2022: 187; 2023: 205; 2024: 145; 2025: 119; 2026: 89.

897 papers.

Sort:

By area:

  1. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  2. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  3. 2021Robust fine-tuning of zero-shot modelscited by 785
  4. 2021Domain Generalization: A Surveycited by 760
  5. 2022Continual Test-Time Domain Adaptationcited by 520
  6. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  7. 2021Intriguing Properties of Vision Transformerscited by 446
  8. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 409
  9. 2023Hyena Hierarchy: Towards Larger Convolutional Language Modelscited by 388
  10. 2021Revisiting the Calibration of Modern Neural Networkscited by 387
  11. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 379
  12. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
38 more
  1. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  2. 2021Transformers Can Do Bayesian Inferencecited by 338
  3. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  4. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  5. 2021Unsolved Problems in ML Safetycited by 291
  6. 2021TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentationcited by 225
  7. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  8. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  9. 2023Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priorscited by 156
  10. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  11. 2023Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuningcited by 150
  12. 2022On Feature Learning in the Presence of Spurious Correlationscited by 145
  13. 2021Towards Robust Vision Transformercited by 137
  14. 2021Adversarial purification with Score-based generative modelscited by 132
  15. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  16. 2023EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizationcited by 123
  17. 20223D Common Corruptions and Data Augmentationcited by 120
  18. 2021Causality-inspired Single-source Domain Generalization for Medical Image Segmentationcited by 118
  19. 2021Predicting with Confidence on Unseen Distributionscited by 116
  20. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  21. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  22. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  23. 2021Measure and Improve Robustness in NLP Models: A Surveycited by 107
  24. 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factorscited by 106
  25. 2021Model-Based Domain Generalizationcited by 103
  26. 2022Robust Mean Teacher for Continual and Gradual Test-Time Adaptationcited by 102
  27. 2023TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptationcited by 101
  28. 2023Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentationcited by 100
  29. 2021On Interaction Between Augmentations and Corruptions in Natural Corruption Robustnesscited by 98
  30. 2022Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptationcited by 98
  31. 2022Image Data Augmentation for Deep Learning: A Surveycited by 96
  32. 2021Towards Principled Disentanglement for Domain Generalizationcited by 91
  33. 2023Leaving Reality to Imagination: Robust Classification via Generated Datasetscited by 91
  34. 2021AugMax: Adversarial Composition of Random Augmentations for Robust Trainingcited by 89
  35. 2023MedViT: A Robust Vision Transformer for Generalized Medical Image Classificationcited by 89
  36. 2021Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoderscited by 88
  37. 2022Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentationcited by 88
  38. 2021Augmentation Strategies for Learning with Noisy Labelscited by 86

50 most cited of 897 All 897 (JSON)