NoisyMix: Boosting Model Robustness to Common Corruptions
Benjamin Erichson, Soon Hoe Lim, Winnie Xu, Francisco Utrera, Ziang Cao, Michael Mahoney
Abstract
The robustness of neural networks has become increasingly important in real-world applications where stable and reliable performance is valued over simply achieving high predictive accuracy. To address this, data augmentation techniques have been shown to improve robustness against input perturbations and domain shifts. In this paper, we propose a new training scheme called NoisyMix that leverages noisy augmentations in both input and feature space to improve model robustness and in-domain accuracy. We demonstrate the effectiveness of NoisyMix on several benchmark datasets, including ImageNet-C, ImageNet-R, and ImageNet-P. Additionally, we provide theoretical analysis to better understand the implicit regularization and robustness properties of NoisyMix.
BibTeX
@InProceedings{pmlr-v238-erichson24a,
title = {{NoisyMix}: Boosting Model Robustness to Common Corruptions},
author = {Erichson, Benjamin and Hoe Lim, Soon and Xu, Winnie and Utrera, Francisco and Cao, Ziang and Mahoney, Michael},
booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics},
pages = {4033--4041},
year = {2024},
editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen},
volume = {238},
series = {Proceedings of Machine Learning Research},
month = {02--04 May},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v238/erichson24a/erichson24a.pdf},
url = {https://proceedings.mlr.press/v238/erichson24a.html},
abstract = {The robustness of neural networks has become increasingly important in real-world applications where stable and reliable performance is valued over simply achieving high predictive accuracy. To address this, data augmentation techniques have been shown to improve robustness against input perturbations and domain shifts. In this paper, we propose a new training scheme called NoisyMix that leverages noisy augmentations in both input and feature space to improve model robustness and in-domain accuracy. We demonstrate the effectiveness of NoisyMix on several benchmark datasets, including ImageNet-C, ImageNet-R, and ImageNet-P. Additionally, we provide theoretical analysis to better understand the implicit regularization and robustness properties of NoisyMix.}
}