Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN), Multi Class Scenarios
This work addresses the need for flexible conditional generation in multi-class settings, though it appears incremental as it builds on existing GAN frameworks.
The paper tackles the problem of generating class-specific samples in multi-class scenarios by introducing VAC+GAN, a method that conditions a GAN generator using a multi-class classifier, achieving results comparable to other methods on two databases.
Conditional generators learn the data distribution for each class in a multi-class scenario and generate samples for a specific class given the right input from the latent space. In this work, a method known as "Versatile Auxiliary Classifier with Generative Adversarial Network" for multi-class scenarios is presented. In this technique, the Generative Adversarial Networks (GAN)'s generator is turned into a conditional generator by placing a multi-class classifier in parallel with the discriminator network and backpropagate the classification error through the generator. This technique is versatile enough to be applied to any GAN implementation. The results on two databases and comparisons with other method are provided as well.