# Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration

arXiv: https://arxiv.org/abs/2202.12412 · HTML: https://mlsanity.com/paper/2202.12412/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 24 Feb 2022.

## Builds on (most cited first, 16 of 16)

- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Verified Uncertainty Calibration](https://mlsanity.com/paper/1909.10155/) (2019)
- [A Fourier Perspective on Model Robustness in Computer Vision](https://mlsanity.com/paper/1906.08988/) (2019)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Do CIFAR-10 Classifiers Generalize to CIFAR-10?](https://mlsanity.com/paper/1806.00451/) (2018)
- [MNIST-C: A Robustness Benchmark for Computer Vision](https://mlsanity.com/paper/1906.02337/) (2019)
- [Adversarial Examples Are a Natural Consequence of Test Error in Noise](https://mlsanity.com/paper/1901.10513/) (2019)
- [Measuring the tendency of CNNs to Learn Surface Statistical Regularities](https://mlsanity.com/paper/1711.11561/) (2017)
- [Excessive Invariance Causes Adversarial Vulnerability](https://mlsanity.com/paper/1811.00401/) (2018)
- [On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions](https://mlsanity.com/paper/1809.04098/) (2018)

## Built on by (most cited first, 7 of 7)

- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [A Survey on the Robustness of Computer Vision Models against Common Corruptions](https://mlsanity.com/paper/2305.06024/) (2023)
- [Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification](https://mlsanity.com/paper/2403.01944/) (2024)
- [Robust Fine-Tuning of Vision-Language Models for Domain Generalization](https://mlsanity.com/paper/2311.02236/) (2023)
- [Dynamic Test-Time Augmentation via Differentiable Functions](https://mlsanity.com/paper/2212.04681/) (2022)
- [DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning](https://mlsanity.com/paper/2308.06622/) (2023)
- [Un-mixing Test-time Adaptation under Heterogeneous Data Streams](https://mlsanity.com/paper/2411.15173/) (2024)

## Abstract (arXiv)

Diverse data augmentation strategies are a natural approach to improving robustness in computer vision models against unforeseen shifts in data distribution. However, the ability to tailor such strategies to inoculate a model against specific classes of corruptions or attacks -- without incurring substantial losses in robustness against other classes of corruptions -- remains elusive. In this work, we successfully harden a model against Fourier-based attacks, while producing superior-to-AugMix accuracy and calibration results on both the CIFAR-10-C and CIFAR-100-C datasets; classification error is reduced by over ten percentage points for some high-severity noise and digital-type corruptions. We achieve this by incorporating Fourier-basis perturbations in the AugMix image-augmentation framework. Thus we demonstrate that the AugMix framework can be tailored to effectively target particular distribution shifts, while boosting overall model robustness.