Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification

Open paper
Benchmark Model Rank Results
adversarial-robustness-on-imagenet-cCCT + PRIME + AFA#5mean Corruption Error (mCE): 52.8
image-classification-on-cifar-10CCT + AFA#148Percentage correct: 95.94
image-classification-on-cifar-100CCT + PRIME + AFA#214Percentage correct: 68.48
image-classification-on-imagenetCCT + AugMix + AFA#918Top 1 Accuracy: 77.4%

Rank counts only results with a code link.