Conditional Generative Adversarial Nets
This work addresses the need for more controllable and versatile generative models in machine learning, representing an incremental advancement over the original GAN framework.
The authors tackled the problem of controlling the output of generative adversarial networks by introducing a conditional version that incorporates additional data into both the generator and discriminator, resulting in the ability to generate MNIST digits based on class labels and produce descriptive tags for images beyond the training set.
Generative Adversarial Nets [8] were recently introduced as a novel way to train generative models. In this work we introduce the conditional version of generative adversarial nets, which can be constructed by simply feeding the data, y, we wish to condition on to both the generator and discriminator. We show that this model can generate MNIST digits conditioned on class labels. We also illustrate how this model could be used to learn a multi-modal model, and provide preliminary examples of an application to image tagging in which we demonstrate how this approach can generate descriptive tags which are not part of training labels.