Perlin random erasing for data augmentation Veri artirma için perlin rastgele silme


Saran M., NAR F. , Saran A. N.

29th IEEE Conference on Signal Processing and Communications Applications, SIU 2021, Virtual, Istanbul, Turkey, 9 - 11 June 2021 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/siu53274.2021.9477804
  • City: Virtual, Istanbul
  • Country: Turkey
  • Keywords: Data augmentation, Deep learning, Random erasing

Abstract

© 2021 IEEE.In the last decade, Deep Learning is applied in a wide range of problems with tremendous success. Large data, increased computational resources, and theoretical improvements are main reasons for this success. As the dataset grows, the realworld is better represented, allows developing a model that can generalize. However, creating a labeled dataset is expensive, timeconsuming, or sometimes even challenging. Therefore, researchers proposed data augmentation methods to increase dataset size by creating variations of the existing data. This study proposes an extension to Random Erasing data augmentation method by introducing smoothness. The proposed method provides better performance compared to Random Erasing data augmentation method, which is shown using a transfer learning scenario on the UC Merced Land-use image dataset.