[IP2-1-1] Data augmentation

Data augmentation refers to a scheme of augmenting the observed data so as to make it more easy to analyze. An application from deep lerarning is to increase the number of input training sample images with augmented data. Examples of data augmentation techniques include horizontal flips, random crops, and principal component analysis.

External resources

• Martin A Tanner and Wing Hung Wong. The calculation of posterior distributions by data augmentation. Journal of the American statistical Association, 1987 ,82(398):528–540.
• Yu, X., Wu, X., Luo, C., & Ren, P. (2017). Deep learning in remote sensing scene classification: a data augmentation enhanced convolutional neural network framework. GIScience & Remote Sensing, 54(5), 741-758. doi:10.1080/15481603.2017.1323377

Learning outcomes

• 1148 - Understand how data augmentation can improve deep learning methods for image classification

  Understand how data augmentation can improve deep learning methods for image classification

Self assessment

Outgoing relations

• [IP2-1-1] Data augmentation subclassof [IP2-1] Data fusion

Contributors

• Florian Albrecht
  https://www.researchgate.net/profile/Florian_Albrecht
• Mariana Belgiu
  https://research.utwente.nl/en/persons/mariana-belgiu
• Stefan Lang
  https://www.uni-salzburg.at/index.php?id=32483&L=1