There are no existing augmentation techniques that can correct adataset that has very poor diversity with respect to the testing data. All these augmenta-tion algorithms perform best under the assumption that the training data and testingdata are both drawn from the same distribution.
Important border to where these can be applied!
suggests that it is best to initially train with the original data only and then finish trainingwith the original and augmented data,
New interesting method of training
A robust classifier is thus defined as having alow variance in predictions across augmentations.
Robust classifier definition
By taking a test image and augmenting it in thesame way as the training images, a more robust prediction can be derived.
Interesting