Peyton Byungju Kim

Same issue here as well. (I also used Pytorch for re-implementation) I hope the authors provide more details and trained parameters for long-tailed CIFAR. @hbsz123 Please let us know if...

Basically it's rule of thumb:) Fortunately, algorithm was not very sensitive to the choice of lambda on our exp. Very sorry for too late response. Byungju Kim

Hi, Riccardo. Try pre-training. Train your network without h network before the adversarial process. When we tried this method, the overall performance had been improved a bit. If it does...

Hi, You can download the Colored-MNIST datasets through the links in this repo. To generate them, I controlled std of sampling distribution. You can find more detailed algorithm from the...

Hi The implementation for Rescale is line245 in "cifar.py".