Greedy AutoAugment

Alireza Naghizadeh, Mohammadsajad Abavisani, Dimitris N. Metaxas

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


A major problem in data augmentation is to ensure that the generated new samples cover the search space. This is a challenging problem and requires exploration for data augmentation policies to ensure their effectiveness in covering the search space. In this paper, we propose Greedy AutoAugment as a highly efficient search algorithm to find the best augmentation policies. We use a greedy approach to reduce the exponential growth of the number of possible trials to linear growth. The Greedy Search also helps us to lead the search towards the sub-policies with better results, which eventually helps to increase the accuracy. The proposed method can be used as a reliable addition to the current artifitial neural networks. Our experiments on four datasets (Tiny ImageNet, CIFAR-10, CIFAR-100, and SVHN) show that Greedy AutoAugment provides better accuracy, while using 360 times fewer computational resources.

Original languageEnglish (US)
Pages (from-to)624-630
Number of pages7
JournalPattern Recognition Letters
StatePublished - Oct 2020

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence
  • Signal Processing
  • Computer Vision and Pattern Recognition


  • ANN
  • Augmentation
  • AutoAugment
  • Classification
  • Neural networks
  • Vision


Dive into the research topics of 'Greedy AutoAugment'. Together they form a unique fingerprint.

Cite this