zj-jayzhang / guided_adversarial_examples Goto Github PK

This is the official PyTorch implementation of Adversarial Examples for Good: Adversarial Examples Guided Imbalanced Learning (ICIP 2022)

We provide several training examples with this repo:

• To train the ERM baseline (CE loss) on long-tailed imbalance with ratio of 100

python cifar_train.py --gpu 0 --imb_type exp --imb_factor 0.01 --loss_type CE --train_rule None

• To train the LDAM-DRW loss training on long-tailed imbalance with ratio of 100

python cifar_train.py --gpu 0 --imb_type exp --imb_factor 0.01 --loss_type LDAM --train_rule DRW

• Use our method to adjust the biased decision boundary

python train_adv.py --gpu 0 --imb_type exp --imb_factor 0.01 --loss_type CE --train_rule None \ 
        --resume checkpoint/cifar10_resnet32_CE_None_exp_0.01_0/ckpt.best.pth.tar --lr 0.001

Note that we just simply finetune the biased model for several epochs, which is very efficient and effective.

@article{zhang2022adversarial,
  title={Adversarial Examples for Good: Adversarial Examples Guided Imbalanced Learning},
  author={Zhang, Jie and Zhang, Lei and Li, Gang and Wu, Chao},
  journal={arXiv preprint arXiv:2201.12356},
  year={2022}
}