/CAAT

Primary LanguagePython

CAAT

This is the code for the paper: Combining Adversaries with Anti-adversaries in Training

Setups

The requiring environment is as bellow:

  • Linux
  • python 3.8
  • pytorch 1.9.0
  • torchvision 0.10.0

Running CAAT on benchmark datasets (CIFAR-10).

Here are two examples for training imbalanced and noisy data:
ResNet32 on CIFAR10-LT with imbalanced factor of 10:

python CAAT.py --dataset cifar10 --imbalanced_factor 10

ResNet32 on noisy CIFAR10 with 20% pair-flip noise:
python CAAT.py --dataset cifar10 --corruption_type flip2 --corruption_ratio 0.2