BAGAN: Data Augmentation with Balancing GAN
This addresses data imbalance in image classification, which negatively affects deep learning models, though it is an incremental improvement over existing GAN-based methods.
The paper tackles the problem of imbalanced image classification datasets by proposing BAGAN, a balancing GAN for data augmentation, which generates high-quality images for minority classes to restore dataset balance and improve classifier accuracy.
Image classification datasets are often imbalanced, characteristic that negatively affects the accuracy of deep-learning classifiers. In this work we propose balancing GAN (BAGAN) as an augmentation tool to restore balance in imbalanced datasets. This is challenging because the few minority-class images may not be enough to train a GAN. We overcome this issue by including during the adversarial training all available images of majority and minority classes. The generative model learns useful features from majority classes and uses these to generate images for minority classes. We apply class conditioning in the latent space to drive the generation process towards a target class. The generator in the GAN is initialized with the encoder module of an autoencoder that enables us to learn an accurate class-conditioning in the latent space. We compare the proposed methodology with state-of-the-art GANs and demonstrate that BAGAN generates images of superior quality when trained with an imbalanced dataset.