Too Long; Didn't Read
Unsupervised Data Augmentation (UDA) assistants us to build a better model by leveraging several data augmentation methods. In natural language processing (NLP) field, it is hard to augmenting text due to high complexity of language. Back translation is a method to leverage translation system to generate data. In computer vision area, generating augmented image in computer vision is relative easier. After generating large enough data set of model training, authors noticed that model can easily over-fit. Therefore, they introduce Training Signal Annealing (TSA) to overcome it.