# NoisyMix: Boosting Model Robustness to Common Corruptions

Source: [NoisyMix: Boosting Model Robustness to Common Corruptions](<https://www.sota2.com/research/paper/68fa6c971e209131cea34af3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:15:31.627Z

Authors: N. Benjamin Erichson, Soon Hoe Lim, Winnie Xu, Francisco Utrera, Ziang Cao, Michael W. Mahoney

Published: 2022-02-02T19:53:35.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on CIFAR-10 (test) (C15/Corruption Metrics)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-c15-corruption-metrics.md>): Image Classification; CIFAR-10 (test); Accuracy: 96.86.

- [Image Classification on CIFAR-100 (test) (Accuracy and Mean Corruption Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-accuracy-and-mean-corruption-accuracy.md>): Image Classification; CIFAR-100 (test); Accuracy: 0.8177.

- [Image Classification on TinyImageNet (test) (Corruption Metrics)](<https://www.sota2.com/research/sota/image-classification-on-tinyimagenet-test-corruption-metrics.md>): Image Classification; TinyImageNet (test); Accuracy: 67.83.

- [Image Classification on CIFAR-10 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test.md>): Image Classification; CIFAR-10 (test); Accuracy: 96.65.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2202.01263>)

[PDF](<https://arxiv.org/pdf/2202.01263.pdf>)