Dynamic Data Augmentation with Gating Networks. (arXiv:2111.03253v2 [cs.LG] UPDATED)

Data augmentation is a technique to improve the generalization ability of
machine learning methods by increasing the size of the dataset. However, since
every augmentation method is not equally effective for every dataset, you need
to select an appropriate method carefully. We propose a neural network that
dynamically selects the best combination of data augmentation methods using a
mutually beneficial gating network and a feature consistency loss. The gating
network is able to control how much of each data augmentation …

arxiv augmentation data networks