On Improving the Performance of Glitch Classification for Gravitational Wave Detection by using Generative Adversarial Networks

TL;DR

This paper introduces a GAN-based data augmentation framework using ProGAN to generate high-resolution spectrograms, significantly improving glitch classification performance in gravitational wave data analysis, especially with limited and imbalanced datasets.

Contribution

The paper presents a novel use of ProGAN for generating high-resolution spectrograms to augment training data, enhancing classification accuracy and robustness in gravitational wave glitch detection.

Findings

GAN-augmented data improves classification accuracy.

Reduces performance fluctuations with small datasets.

Provides an alternative to transfer learning for spectrogram classification.

Abstract

Spectrogram classification plays an important role in analyzing gravitational wave data. In this paper, we propose a framework to improve the classification performance by using Generative Adversarial Networks (GANs). As substantial efforts and expertise are required to annotate spectrograms, the number of training examples is very limited. However, it is well known that deep networks can perform well only when the sample size of the training set is sufficiently large. Furthermore, the imbalanced sample sizes in different classes can also hamper the performance. In order to tackle these problems, we propose a GAN-based data augmentation framework. While standard data augmentation methods for conventional images cannot be applied on spectrograms, we found that a variant of GANs, ProGAN, is capable of generating high-resolution spectrograms which are consistent with the quality of the high-resolution original images and provide a desirable diversity. We have validated our framework by classifying glitches in the {\it Gravity Spy} dataset with the GAN-generated spectrograms for training. We show that the proposed method can provide an alternative to transfer learning for the classification of spectrograms using deep networks, i.e. using a high-resolution GAN for data augmentation instead. Furthermore, fluctuations in classification performance with small sample sizes for training and evaluation can be greatly reduced. Using the trained network in our framework, we have also examined the spectrograms with label anomalies in {\it Gravity Spy}.