Learning to Compose Domain-Specific Transformations for Data Augmentation
This work addresses the challenge for machine learning practitioners who need efficient data augmentation to improve model performance without extensive manual tuning.
The paper tackles the problem of automating the composition of domain-specific transformations for data augmentation, which is typically manual and time-consuming, and achieves improvements such as 4.0 accuracy points on CIFAR-10 and 3.4 accuracy points on a medical imaging dataset compared to standard methods.
Data augmentation is a ubiquitous technique for increasing the size of labeled training sets by leveraging task-specific data transformations that preserve class labels. While it is often easy for domain experts to specify individual transformations, constructing and tuning the more sophisticated compositions typically needed to achieve state-of-the-art results is a time-consuming manual task in practice. We propose a method for automating this process by learning a generative sequence model over user-specified transformation functions using a generative adversarial approach. Our method can make use of arbitrary, non-deterministic transformation functions, is robust to misspecified user input, and is trained on unlabeled data. The learned transformation model can then be used to perform data augmentation for any end discriminative model. In our experiments, we show the efficacy of our approach on both image and text datasets, achieving improvements of 4.0 accuracy points on CIFAR-10, 1.4 F1 points on the ACE relation extraction task, and 3.4 accuracy points when using domain-specific transformation operations on a medical imaging dataset as compared to standard heuristic augmentation approaches.