# A Fourier Perspective on Model Robustness in Computer Vision

arXiv: https://arxiv.org/abs/1906.08988 · HTML: https://mlsanity.com/paper/1906.08988/

## Key facts

- Cited by 288 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jun 2019.

## Built on by (most cited first, 30 of 288)

- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [How Do Vision Transformers Work?](https://mlsanity.com/paper/2202.06709/) (2022)
- [Vision Transformers are Robust Learners](https://mlsanity.com/paper/2105.07581/) (2021)
- [FreeU: Free Lunch in Diffusion U-Net](https://mlsanity.com/paper/2309.11497/) (2023)
- [PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures](https://mlsanity.com/paper/2112.05135/) (2021)
- [Frequency Domain Model Augmentation for Adversarial Attack](https://mlsanity.com/paper/2207.05382/) (2022)
- [Inception Transformer](https://mlsanity.com/paper/2205.12956/) (2022)
- [On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness](https://mlsanity.com/paper/2102.11273/) (2021)
- [A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking](https://mlsanity.com/paper/2302.14301/) (2023)
- [Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity](https://mlsanity.com/paper/2203.05151/) (2022)
- [Improving Vision Transformers by Revisiting High-frequency Components](https://mlsanity.com/paper/2204.00993/) (2022)
- [On the effectiveness of adversarial training against common corruptions](https://mlsanity.com/paper/2103.02325/) (2021)
- [Benchmarking and Analyzing Point Cloud Classification under Corruptions](https://mlsanity.com/paper/2202.03377/) (2022)
- [Editing a classifier by rewriting its prediction rules](https://mlsanity.com/paper/2112.01008/) (2021)
- [On the Foundations of Shortcut Learning](https://mlsanity.com/paper/2310.16228/) (2023)
- [A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness](https://mlsanity.com/paper/2106.09129/) (2021)
- [Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs](https://mlsanity.com/paper/2110.02797/) (2021)
- [Causally motivated Shortcut Removal Using Auxiliary Labels](https://mlsanity.com/paper/2105.06422/) (2021)
- [Open-Vocabulary Segmentation with Semantic-Assisted Calibration](https://mlsanity.com/paper/2312.04089/) (2023)
- [Spectrum-guided Multi-granularity Referring Video Object Segmentation](https://mlsanity.com/paper/2307.13537/) (2023)
- [Frequency-aware Feature Fusion for Dense Image Prediction](https://mlsanity.com/paper/2408.12879/) (2024)
- [Adaptive Frequency Filters As Efficient Global Token Mixers](https://mlsanity.com/paper/2307.14008/) (2023)
- [Deep Frequency Filtering for Domain Generalization](https://mlsanity.com/paper/2203.12198/) (2022)
- [EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones](https://mlsanity.com/paper/2211.09703/) (2022)
- [When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks](https://mlsanity.com/paper/2105.06152/) (2021)
- [Fighting deepfakes by detecting GAN DCT anomalies](https://mlsanity.com/paper/2101.09781/) (2021)
- [Pyramid Adversarial Training Improves ViT Performance](https://mlsanity.com/paper/2111.15121/) (2021)
- [PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization](https://mlsanity.com/paper/2212.00979/) (2022)
- [Spectral Bias in Practice: The Role of Function Frequency in Generalization](https://mlsanity.com/paper/2110.02424/) (2021)

## Abstract (arXiv)

Achieving robustness to distributional shift is a longstanding and challenging goal of computer vision. Data augmentation is a commonly used approach for improving robustness, however robustness gains are typically not uniform across corruption types. Indeed increasing performance in the presence of random noise is often met with reduced performance on other corruptions such as contrast change. Understanding when and why these sorts of trade-offs occur is a crucial step towards mitigating them. Towards this end, we investigate recently observed trade-offs caused by Gaussian data augmentation and adversarial training. We find that both methods improve robustness to corruptions that are concentrated in the high frequency domain while reducing robustness to corruptions that are concentrated in the low frequency domain. This suggests that one way to mitigate these trade-offs via data augmentation is to use a more diverse set of augmentations. Towards this end we observe that AutoAugment, a recently proposed data augmentation policy optimized for clean accuracy, achieves state-of-the-art robustness on the CIFAR-10-C benchmark.