What is Data Augmentation?
Data augmentation is a technique that can be used to artificially enlarge the size of a training set by creating modified data from the existing one. It is good practice to use data augmentation if you want to avoid overfitting the neural network, or the initial data set is too small to train on, or even if you want to squeeze better performance out of the model.
The use of data augmentation techniques is very common nowadays, although it is not only limited to the field of artificial intelligence but has many other applications. Example data augmentation techniques are presented in the diagram below.
