Data Augmentation Using GANs

Abstract

In this paper we propose the use of Generative Adversarial Networks (GAN) to generate artificial training data for machine learning tasks. The generation of artificial training data can be extremely useful in situations such as imbalanced data sets, performing a role similar to SMOTE or ADASYN. It is also useful when the data contains sensitive information, and it is desirable to avoid using the original data set as much as possible (example: medical data). We test our proposal on benchmark data sets using different network architectures, and show that a Decision Tree (DT) classifier trained using the training data generated by the GAN reached the same, (and surprisingly sometimes better), accuracy and recall than a DT trained on the original data set.

Submitted for ACML 2019

References in corpus (2)

• SMOTE: Synthetic Minority Over-sampling Technique
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

Cited by in corpus (20)

• Generative adversarial network with object detector discriminator for enhanced defect detection on ultrasonic B-scans
• Style-based quantum generative adversarial networks for Monte Carlo events
• Large image datasets: A pyrrhic win for computer vision?
• Not Enough Data? Deep Learning to the Rescue!
• Overcoming limited battery data challenges: A coupled neural network approach
• Synthetic Data Generation for Fraud Detection using GANs
• HyPhy: Deep Generative Conditional Posterior Mapping of Hydrodynamical Physics
• Model-Informed Generative Adversarial Network (MI-GAN) for Learning Optimal Power Flow
• A Novel Resampling Technique for Imbalanced Dataset Optimization
• EfficientSeg: An Efficient Semantic Segmentation Network
• MixBoost: Synthetic Oversampling with Boosted Mixup for Handling Extreme Imbalance
• Modeling EEG data distribution with a Wasserstein Generative Adversarial Network to predict RSVP Events
• WSAM: Visual Explanations from Style Augmentation as Adversarial Attacker and Their Influence in Image Classification
• Adversarial Imitation Learning with Trajectorial Augmentation and Correction
• Quantum generative modeling for financial time series with temporal correlations
• Cross-Domain Image Classification through Neural-Style Transfer Data Augmentation
• OCT-GAN: Neural ODE-based Conditional Tabular GANs
• Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space
• Regularising Deep Networks with Deep Generative Models
• Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding