Research map / Adversarial robustness and security / Certified and empirical robustness
A Fourier Perspective on Model Robustness in Computer Vision
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Gaussian data augmentation | Naturally trained WRN · CIFAR-10-C contrast | accuracy: 0.8225 -> 0.5703 | Hurt |
| add Gaussian data augmentation | Naturally trained WRN · CIFAR-10-C impulse noise | accuracy: 0.5428 -> 0.8308 | Helped |
| add adversarial training | Naturally trained WRN · CIFAR-10-C contrast | accuracy: 0.8225 -> 0.7700 | Hurt |
| add adversarial training | Naturally trained WRN · CIFAR-10-C average | accuracy: 0.7728 -> 0.8095; mCE 1.0825 | Mixed |
| add AutoAugment (brightness/contrast removed) | Naturally trained WRN · CIFAR-10-C average | accuracy: 0.7728 -> 0.8613 | Helped |
| add AutoAugment | Naturally trained ResNet-50 · ImageNet-C average | accuracy: 0.5092 -> 0.5876 | Helped |
| add low pass filter front end | Naturally trained WRN · CIFAR-10-C average | accuracy: 0.7728 -> 0.8299 | Helped |
| add low pass filter front end | Naturally trained WRN · CIFAR-10-C contrast | accuracy: 0.8225 -> 0.6917 | Hurt |
| add high pass filter front end | Naturally trained WRN · CIFAR-10-C average | accuracy: 0.7728 -> 0.6754 | Hurt |
| train with fog-matched Fourier noise augmentation (ablation) | Naturally trained WRN · CIFAR-10-C fog severity 5 | accuracy: 0.7429 -> 0.4626 | Hurt |
| train with fog-matched Fourier noise augmentation (ablation) | Naturally trained WRN · CIFAR-10-C fog severity 1 | accuracy: 0.9606 -> 0.9090 | Hurt |
| add Gaussian augmentation | Naturally trained ResNet-50 · ImageNet-C average | accuracy: 0.5092 -> 0.5741 | Helped |
Closest papers by meaning
- Improving robustness against common corruptions by covariate shift adaptation (NeurIPS 2020 · similarity 0.90)
- Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification (CVPR 2024 · similarity 0.90)
- A Flat Minima Perspective on Understanding Augmentations and Model Robustness (AAAI 2026 · similarity 0.88)
- Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation (ICML 2025 · similarity 0.87)
- LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models (ICML 2025 · similarity 0.86)
- D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Amplitude and Pixel Spaces (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.