Data Augmentation in Emotion Classification Using Generative Adversarial Networks

TL;DR

This paper introduces a GAN-based data augmentation framework for emotion classification, addressing class imbalance and improving accuracy by 5-10% on benchmark datasets.

Contribution

It presents a novel GAN-based data augmentation method using CycleGAN and CNN for emotion classification with imbalanced data.

Findings

Achieved 5-10% increase in classification accuracy

Validated effectiveness on three benchmark datasets

Proposed evaluation methods for GAN performance

Abstract

It is a difficult task to classify images with multiple class labels using only a small number of labeled examples, especially when the label (class) distribution is imbalanced. Emotion classification is such an example of imbalanced label distribution, because some classes of emotions like \emph{disgusted} are relatively rare comparing to other labels like {\it happy or sad}. In this paper, we propose a data augmentation method using generative adversarial networks (GAN). It can complement and complete the data manifold and find better margins between neighboring classes. Specifically, we design a framework with a CNN model as the classifier and a cycle-consistent adversarial networks (CycleGAN) as the generator. In order to avoid gradient vanishing problem, we employ the least-squared loss as adversarial loss. We also propose several evaluation methods on three benchmark datasets to validate GAN's performance. Empirical results show that we can obtain 5%~10% increase in the classification accuracy after employing the GAN-based data augmentation techniques.