Smart Augmentation - Learning an Optimal Data Augmentation Strategy
This addresses the data scarcity issue for neural network practitioners, offering a novel augmentation strategy that can improve performance and reduce network size, though it appears incremental relative to existing techniques like data augmentation and dropout.
The paper tackles the problem of insufficient data for training deep neural networks by introducing Smart Augmentation, a method that learns to generate augmented data during training to reduce loss, resulting in increased accuracy and reduced overfitting across all tested datasets.
A recurring problem faced when training neural networks is that there is typically not enough data to maximize the generalization capability of deep neural networks(DNN). There are many techniques to address this, including data augmentation, dropout, and transfer learning. In this paper, we introduce an additional method which we call Smart Augmentation and we show how to use it to increase the accuracy and reduce overfitting on a target network. Smart Augmentation works by creating a network that learns how to generate augmented data during the training process of a target network in a way that reduces that networks loss. This allows us to learn augmentations that minimize the error of that network. Smart Augmentation has shown the potential to increase accuracy by demonstrably significant measures on all datasets tested. In addition, it has shown potential to achieve similar or improved performance levels with significantly smaller network sizes in a number of tested cases.