Greedy AutoAugment

Alireza Naghizadeh, Mohammadsajad Abavisani, Dimitris N. Metaxas

Abstract: Highlights•The greedy AutoAugment is proposed to find the best augmentation policies.•It reduces the exponential growth of the number of possible trials to linear growth.•The algorithm is computationally efficient and can concatenate many sub-policies.•The greedy approach helps the algorithm to increase the accuracy of the network.