Mixup data augmentation

[sgugger]

@KevinB

So how effective has mixup been in your experience? It seems similar to dropout but instead of setting the value to 0 you are setting it to another value from a random picture and it happens during the data transform process.

It has proved very powerful as a regularization technique (which also means you can reduce dropout, weight decay…)

@xeTaiz

Have you tried mixup with anything else but classification?

Yes, I’ve tried it in NLP, mixing the outputs of the embedding layers and it has given good results. Hoping to have time to experiment with this more and write a paper about it when the development of fastai_v1 slows down a bit I think it would also be helpful in tabular data (again mixing the embeddings fro categorical variables), not sure about object detection since I don’t see how you mixup the targets (which is critical in making mixup work properly).