DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification
arXiv:1809.00981
Abstract
Deep learning has revolutionized the performance of classification, but meanwhile demands sufficient labeled data for training. Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge remains if one tries to train deep networks, especially in the ill-posed extremely low data regimes: only a small set of labeled data are available, and nothing -- including unlabeled data -- else. Such regimes arise from practical situations where not only data labeling but also data collection itself is expensive. We propose a deep adversarial data augmentation (DADA) technique to address the problem, in which we elaborately formulate data augmentation as a problem of training a class-conditional and supervised generative adversarial network (GAN). Specifically, a new discriminator loss is proposed to fit the goal of data augmentation, through which both real and augmented samples are enforced to contribute to and be consistent in finding the decision boundaries. Tailored training techniques are developed accordingly. To quantitatively validate its effectiveness, we first perform extensive simulations to show that DADA substantially outperforms both traditional data augmentation and a few GAN-based options. We then extend experiments to three real-world small labeled datasets where existing data augmentation and/or transfer learning strategies are either less effective or infeasible. All results endorse the superior capability of DADA in enhancing the generalization ability of deep networks trained in practical extremely low data regimes. Source code is available at https://github.com/SchafferZhang/DADA.
arXiv comment15 pages, 5 figures
References in corpus (14)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- The Effectiveness of Data Augmentation in Image Classification using Deep Learning
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- Data Augmentation Generative Adversarial Networks
- Semi-Supervised Learning with Ladder Networks
- Semi-Supervised Learning with Generative Adversarial Networks
- Do GANs actually learn the distribution? An empirical study
- A Bayesian Data Augmentation Approach for Learning Deep Models
- Generative Adversarial Residual Pairwise Networks for One Shot Learning
- Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition
- Lifelong Learning CRF for Supervised Aspect Extraction