Semi-Supervised Learning with Generative Adversarial Networks
This work addresses the challenge of limited labeled data for classification tasks, offering an incremental improvement over existing GAN methods.
The paper tackles the problem of semi-supervised learning by extending Generative Adversarial Networks (GANs) to force the discriminator to output class labels, resulting in a more data-efficient classifier and higher quality generated samples than regular GANs.
We extend Generative Adversarial Networks (GANs) to the semi-supervised context by forcing the discriminator network to output class labels. We train a generative model G and a discriminator D on a dataset with inputs belonging to one of N classes. At training time, D is made to predict which of N+1 classes the input belongs to, where an extra class is added to correspond to the outputs of G. We show that this method can be used to create a more data-efficient classifier and that it allows for generating higher quality samples than a regular GAN.