# NoisyMix: Boosting Model Robustness to Common Corruptions

arXiv: https://arxiv.org/abs/2202.01263 · HTML: https://mlsanity.com/paper/2202.01263/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 76 references that are in the map.
- First posted on arXiv 2 Feb 2022.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Overfitting in adversarially robust deep learning](https://mlsanity.com/paper/2002.11569/) (2020)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [Using Pre-Training Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1901.09960/) (2019)
- [Do Adversarially Robust ImageNet Models Transfer Better?](https://mlsanity.com/paper/2007.08489/) (2020)
- [A Fourier Perspective on Model Robustness in Computer Vision](https://mlsanity.com/paper/1906.08988/) (2019)
- [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](https://mlsanity.com/paper/2009.06962/) (2020)
- [Adversarial Attacks and Defences: A Survey](https://mlsanity.com/paper/1810.00069/) (2018)
- [Fixing Data Augmentation to Improve Adversarial Robustness](https://mlsanity.com/paper/2103.01946/) (2021)
- [How Does Mixup Help With Robustness and Generalization?](https://mlsanity.com/paper/2010.04819/) (2020)
- [On the Origin of Implicit Regularization in Stochastic Gradient Descent](https://mlsanity.com/paper/2101.12176/) (2021)
- [Revisiting ResNets: Improved Training and Scaling Strategies](https://mlsanity.com/paper/2103.07579/) (2021)

## Built on by (most cited first, 17 of 17)

- [Robustness of SAM: Segment Anything Under Corruptions and Beyond](https://mlsanity.com/paper/2306.07713/) (2023)
- [A Survey on the Robustness of Computer Vision Models against Common Corruptions](https://mlsanity.com/paper/2305.06024/) (2023)
- [Can Biases in ImageNet Models Explain Generalization?](https://mlsanity.com/paper/2404.01509/) (2024)
- [Classification robustness to common optical aberrations](https://mlsanity.com/paper/2308.15499/) (2023)
- [Tailoring Mixup to Data for Calibration](https://mlsanity.com/paper/2311.01434/) (2023)
- [Dynamic Test-Time Augmentation via Differentiable Functions](https://mlsanity.com/paper/2212.04681/) (2022)
- [How Do Training Methods Influence the Utilization of Vision Models?](https://mlsanity.com/paper/2410.14470/) (2024)
- [Universum-inspired Supervised Contrastive Learning](https://mlsanity.com/paper/2204.10695/) (2022)
- [Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance](https://mlsanity.com/paper/2402.19401/) (2024)
- [Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models](https://mlsanity.com/paper/2504.18510/) (2025)
- [Curvature Enhanced Data Augmentation for Regression](https://mlsanity.com/paper/2506.06853/) (2025)
- [Improving Mixup Calibration with Wasserstein Distributionally Robust Optimization](https://mlsanity.com/paper/2506.17874/) (2025)
- [One Model, Many Behaviors: Training-Induced Effects on Out-of-Distribution Detection](https://mlsanity.com/paper/2601.10836/) (2026)
- [Don't Look into the Sun: Adversarial Solarization Attacks on Image Classifiers](https://mlsanity.com/paper/2308.12661/) (2023)
- [Global Average Feature Augmentation for Robust Semantic Segmentation with Transformers](https://mlsanity.com/paper/2412.01941/) (2024)
- [Combined Image Data Augmentations diminish the benefits of Adaptive Label Smoothing](https://mlsanity.com/paper/2507.16427/) (2025)
- [Stylized Synthetic Augmentation further improves Corruption Robustness](https://mlsanity.com/paper/2512.15675/) (2025)

## Abstract (arXiv)

For many real-world applications, obtaining stable and robust statistical performance is more important than simply achieving state-of-the-art predictive test accuracy, and thus robustness of neural networks is an increasingly important topic. Relatedly, data augmentation schemes have been shown to improve robustness with respect to input perturbations and domain shifts. Motivated by this, we introduce NoisyMix, a novel training scheme that promotes stability as well as leverages noisy augmentations in input and feature space to improve both model robustness and in-domain accuracy. NoisyMix produces models that are consistently more robust and that provide well-calibrated estimates of class membership probabilities. We demonstrate the benefits of NoisyMix on a range of benchmark datasets, including ImageNet-C, ImageNet-R, and ImageNet-P. Moreover, we provide theory to understand implicit regularization and robustness of NoisyMix.