MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators

arXiv:2107.07260v3 Announce Type: replace
Abstract: We propose a framework of generative adversarial networks with multiple discriminators, which collaborate to represent a real dataset more effectively. Our approach facilitates learning a generator consistent with the underlying data distribution based on real images and thus mitigates the chronic mode collapse problem. From the inspiration of multiple choice learning, we guide each discriminator to have expertise in a subset of the entire data and allow the generator to find reasonable correspondences between the …

abstract adversarial arxiv consistent cs.lg data dataset distribution framework gan generative generative adversarial networks generator images inspiration multiple networks type