mlsanityData to 7 Oct 2026

Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration

arXiv 2202.12412 ↗First posted 24 Feb 2022cs.CV cs.LGcited by 7

Not on the map. Why?

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.

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

Builds on

16 of 23 references.

References · 16

  1. 2016Wide Residual Networkscited by 3,057
  2. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  3. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  4. 2019Natural Adversarial Examplescited by 1,401
  5. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  6. 2016Universal adversarial perturbationscited by 774
  7. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  8. 2019Verified Uncertainty Calibrationcited by 307
  9. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  10. 2018Generalisation in humans and deep neural networkscited by 237
  11. 2018Do CIFAR-10 Classifiers Generalize to CIFAR-10?cited by 197
  12. 2019MNIST-C: A Robustness Benchmark for Computer Visioncited by 137
4 more
  1. 2019Adversarial Examples Are a Natural Consequence of Test Error in Noisecited by 114
  2. 2017Measuring the tendency of CNNs to Learn Surface Statistical Regularitiescited by 87
  3. 2018Excessive Invariance Causes Adversarial Vulnerabilitycited by 66
  4. 2018On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functionscited by 31

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 2.

7 papers.

  1. 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 246
  2. 2023A Survey on the Robustness of Computer Vision Models against Common Corruptionscited by 20
  3. 2024Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classificationcited by 18
  4. 2023Robust Fine-Tuning of Vision-Language Models for Domain Generalizationcited by 7
  5. 2022Dynamic Test-Time Augmentation via Differentiable Functionscited by 4
  6. 2023DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learningcited by 4
  7. 2024Un-mixing Test-time Adaptation under Heterogeneous Data Streamscited by 0