MR-GAN: Manifold Regularized Generative Adversarial Networks
arXiv:1811.10427
Abstract
Despite the growing interest in generative adversarial networks (GANs), training GANs remains a challenging problem, both from a theoretical and a practical standpoint. To address this challenge, in this paper, we propose a novel way to exploit the unique geometry of the real data, especially the manifold information. More specifically, we design a method to regularize GAN training by adding an additional regularization term referred to as manifold regularizer. The manifold regularizer forces the generator to respect the unique geometry of the real data manifold and generate high quality data. Furthermore, we theoretically prove that the addition of this regularization term in any class of GANs including DCGAN and Wasserstein GAN leads to improved performance in terms of generalization, existence of equilibrium, and stability. Preliminary experiments show that the proposed manifold regularization helps in avoiding mode collapse and leads to stable training.
arXiv commentarXiv admin note: text overlap with arXiv:1706.04156 by other authors
References in corpus (15)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Improved Techniques for Training GANs
- Towards Principled Methods for Training Generative Adversarial Networks
- Mode Regularized Generative Adversarial Networks
- Stabilizing Training of Generative Adversarial Networks through Regularization
- Deep Learning Face Attributes in the Wild
- Gradient descent GAN optimization is locally stable
- Geometry Score: A Method For Comparing Generative Adversarial Networks
- Improved generator objectives for GANs
- Disconnected Manifold Learning for Generative Adversarial Networks
- Is Generator Conditioning Causally Related to GAN Performance?
- Reachability Analysis of Deep Neural Networks with Provable Guarantees
- Semi-Supervised Learning with GANs: Revisiting Manifold Regularization
- MMGAN: Manifold Matching Generative Adversarial Network