# Virtual Conditional Generative Adversarial Networks

## TL;DR

This paper introduces vcGAN, a novel GAN variant that combines ensemble and conditional GAN features, enabling training on unlabeled data with improved convergence and sample quality, while requiring minimal additional parameters.

## Contribution

The paper proposes vcGAN, a new GAN architecture that efficiently combines ensemble and conditional capabilities without explicit clustering or extra parameters.

## Key findings

- vcGAN converges faster than traditional GANs.
- vcGAN achieves lower FID scores on multiple datasets.
- The ADC learns categorical probabilities and enables class-conditional sampling.

## Abstract

When trained on multimodal image datasets, normal Generative Adversarial Networks (GANs) are usually outperformed by class-conditional GANs and ensemble GANs, but conditional GANs is restricted to labeled datasets and ensemble GANs lack efficiency. We propose a novel GAN variant called virtual conditional GAN (vcGAN) which is not only an ensemble GAN with multiple generative paths while adding almost zero network parameters, but also a conditional GAN that can be trained on unlabeled datasets without explicit clustering steps or objectives other than the adversary loss. Inside the vcGAN's generator, a learnable ``analog-to-digital converter (ADC)" module maps a slice of the inputted multivariate Gaussian noise to discrete/digital noise (virtual label), according to which a selector selects the corresponding generative path to produce the sample. All the generative paths share the same decoder network while in each path the decoder network is fed with a concatenation of a different pre-computed amplified one-hot vector and the inputted Gaussian noise. We conducted a lot of experiments on several balanced/imbalanced image datasets to demonstrate that vcGAN converges faster and achieves improved Frech\'et Inception Distance (FID). In addition, we show the training byproduct that the ADC in vcGAN learned the categorical probability of each mode and that each generative path generates samples of specific mode, which enables class-conditional sampling. Codes are available at \url{https://github.com/annonnymmouss/vcgan}