eGAN: Unsupervised Approach to Class Imbalance Using Transfer Learning

Class imbalance is an inherent problem in many machine learning classification tasks. This often leads to learned models that are unusable for any practical purpose. In this study, we explore unsupervised approach address class by leveraging transfer from pre-trained image models. To end, encoder-based Generative Adversarial Network (eGAN) proposed which modifies the generator of a GAN introducing encoder module and adopts loss function directly classify majority minority class. best our knowledge, first work tackle using GAN-based rather than augmenting dataset with synthesized fake images. Our eliminates epistemic uncertainty model predictions, as \(P(minority)\) \(P(majority)\) need not sum up 1. The impact combinations different at discriminator level also explored. Best result 0.69 F1-score was obtained on CIFAR-10 task enforced ratio 1:2500. implementation code available - https://github.com/demolakstate/eGAN_addressing_class_imbalance_with_transfer_learning_on_GAN.git.