Ensembles of Generative Adversarial Networks for Disconnected Data

Understand

Most current computer vision datasets are composed of disconnected sets, such as images from different classes.

• We prove that distributions of this type of data cannot be represented with a continuous generative network without error.
• They can be represented in two ways: With an ensemble of networks or with a single network with truncated latent space.
• We show that ensembles are more desirable than truncated distributions in practice.