Details

Autor(en) / Beteiligte

• Zhang, Xiaofeng
• Wang, Zhangyang
• Liu, Dong
• Ling, Qing

Titel

DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification

Ist Teil von

• ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, p.2807-2811

Ort / Verlag

IEEE

Erscheinungsjahr

2019

Link zum Volltext

• IEEE_Xplore

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• 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. Source code is available at https://github.com/SchafferZhang/DADA.