Towards Imbalanced Image Classification: A Generative Adversarial Network Ensemble Learning Method

Abstract

Learning from minority class has been a significant and challenging task which has many potential applications. Weather classification is such a case of imbalanced label distribution. This is because in places like Beijing, some types of weather, such as rain and snow, are relatively rare compared to sunny and haze days. Existing methods are primary to classify the weather conditions relying on expensive sensors or human assistance, which however usually are expensive and time-consuming. In this paper, we propose a new ensemble framework based on the advanced generative adversarial network and an effective data cleaning way to address the class imbalance problem for weather classification. The proposed method not only generates new and reliable samples for the minority class to restore balance, but also filters those generated samples which are unreliable. Experiments show that our approach outperforms the state-of-the-art methods by a huge margin for imbalanced weather classification on several benchmark data sets.

Keywords

• Imbalanced learning
• GAN
• data augmentation
• data cleaning
• boosting
• weather classification