CEGAN: Classification Enhancement Generative Adversarial Networks for unraveling data imbalance problems

Sungho Suh, Haebom Lee, Paul Lukowicz, Yong Oh Lee

Abstract: Highlights•A classification enhancement generative adversarial networks (CEGAN) is introduced to improve the classification under the imbalanced data condition.•The proposed method is composed of three independent networks, a generator, a discriminator, and a classifier.•By designing a loss function for ambiguous classes, we propose a classification enhancement GAN for ambiguity reduction (CEGAN-AR).•The proposed method outperforms various standard data augmentation methods under data imbalanced conditions.