Learning to Compose Domain-Specific Transformations for Data Augmentation

Abstract

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.

To appear at Neural Information Processing Systems (NIPS) 2017

References in corpus (2)

• Explaining and Harnessing Adversarial Examples
• Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks

Cited by in corpus (18)

• Albumentations: fast and flexible image augmentations
• A Comprehensive Survey of Image Augmentation Techniques for Deep Learning
• A Survey on Data Augmentation for Text Classification
• Hydra: an Ensemble of Convolutional Neural Networks for Geospatial Land Classification
• Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification
• Further advantages of data augmentation on convolutional neural networks
• A survey of synthetic data augmentation methods in computer vision
• AADG: Automatic Augmentation for Domain Generalization on Retinal Image Segmentation
• Data augmentation using learned transformations for one-shot medical image segmentation
• OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
• Neural Transformation Learning for Deep Anomaly Detection Beyond Images
• PointAugment: an Auto-Augmentation Framework for Point Cloud Classification
• PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds
• Revisiting Meta-Learning as Supervised Learning
• ReSmooth: Detecting and Utilizing OOD Samples when Training with Data Augmentation
• On the Pitfalls of Learning with Limited Data: A Facial Expression Recognition Case Study
• Generative Adversarial Data Programming
• What augmentations are sensitive to hyper-parameters and why?