Diversity Regularized Adversarial Learning

Abstract

The two key players in Generative Adversarial Networks (GANs), the discriminator and generator, are usually parameterized as deep neural networks (DNNs). On many generative tasks, GANs achieve state-of-the-art performance but are often unstable to train and sometimes miss modes. A typical failure mode is the collapse of the generator to a single parameter configuration where its outputs are identical. When this collapse occurs, the gradient of the discriminator may point in similar directions for many similar points. We hypothesize that some of these shortcomings are in part due to primitive and redundant features extracted by discriminator and this can easily make the training stuck. We present a novel approach for regularizing adversarial models by enforcing diverse feature learning. In order to do this, both generator and discriminator are regularized by penalizing both negatively and positively correlated features according to their differentiation and based on their relative cosine distances. In addition to the gradient information from the adversarial loss made available by the discriminator, diversity regularization also ensures that a more stable gradient is provided to update both the generator and discriminator. Results indicate our regularizer enforces diverse features, stabilizes training, and improves image synthesis.

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Improved Training of Wasserstein GANs
• Improved Techniques for Training GANs
• Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
• Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• Towards Principled Methods for Training Generative Adversarial Networks
• Neural Photo Editing with Introspective Adversarial Networks
• Stabilizing Training of Generative Adversarial Networks through Regularization
• Regularizing CNNs with Locally Constrained Decorrelations
• Convolutional Clustering for Unsupervised Learning
• Deep Learning of Nonnegativity-Constrained Autoencoders for Enhanced Understanding of Data
• Building Efficient ConvNets using Redundant Feature Pruning
• On the Generalization Error Bounds of Neural Networks under Diversity-Inducing Mutual Angular Regularization
• Variance Regularizing Adversarial Learning