MAGAN: Margin Adaptation for Generative Adversarial Networks

Abstract

We propose the Margin Adaptation for Generative Adversarial Networks (MAGANs) algorithm, a novel training procedure for GANs to improve stability and performance by using an adaptive hinge loss function. We estimate the appropriate hinge loss margin with the expected energy of the target distribution, and derive principled criteria for when to update the margin. We prove that our method converges to its global optimum under certain assumptions. Evaluated on the task of unsupervised image generation, the proposed training procedure is simple yet robust on a diverse set of data, and achieves qualitative and quantitative improvements compared to the state-of-the-art.

References in corpus (4)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Improved Training of Wasserstein GANs
• Improved Techniques for Training GANs
• Energy-based Generative Adversarial Network

Cited by in corpus (12)

• How Generative Adversarial Networks and Their Variants Work: An Overview
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation
• Dual Discriminator Generative Adversarial Nets
• Robust Imitation of Diverse Behaviors
• Multi-Generator Generative Adversarial Nets
• Hierarchical Behavioral Repertoires with Unsupervised Descriptors
• Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures
• Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images
• GANs beyond divergence minimization
• Complexity Controlled Generative Adversarial Networks
• Fast Face Image Synthesis with Minimal Training