MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators

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 latent and real data spaces automatically without extra supervision for training examples. Despite the use of multiple discriminators, the backbone networks are shared across the discriminators and the increase in training cost is marginal. We demonstrate the effectiveness of our algorithm using multiple evaluation metrics in the standard datasets for diverse tasks.

arXiv commentNeurIPS 2022

References in corpus (16)

• Auto-Encoding Variational Bayes
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Energy-based Generative Adversarial Network
• The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
• Adversarial Feature Learning
• Adversarially Learned Inference
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• Assessing Generative Models via Precision and Recall
• AdaGAN: Boosting Generative Models
• Diversity-Sensitive Conditional Generative Adversarial Networks
• Stabilizing GAN Training with Multiple Random Projections
• On GANs and GMMs
• Multi-objective training of Generative Adversarial Networks with multiple discriminators
• Confident Multiple Choice Learning