Open AccessProceedings Article
Improved training of wasserstein GANs
Ishaan Gulrajani,Faruk Ahmed,Martin Arjovsky,Vincent Dumoulin,Aaron Courville +4 more
- Vol. 30, pp 5769-5779
TLDR
The authors proposed to penalize the norm of the gradient of the critic with respect to its input to improve the training stability of Wasserstein GANs and achieve stable training of a wide variety of GAN architectures with almost no hyperparameter tuning.Abstract:
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only poor samples or fail to converge. We find that these problems are often due to the use of weight clipping in WGAN to enforce a Lipschitz constraint on the critic, which can lead to undesired behavior. We propose an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input. Our proposed method performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning, including 101-layer ResNets and language models with continuous generators. We also achieve high quality generations on CIFAR-10 and LSUN bedrooms.read more
Citations
More filters
Posted Content
Detection, Attribution and Localization of GAN Generated Images
Michael Goebel,Lakshmanan Nataraj,Tejaswi Nanjundaswamy,Tajuddin Manhar Mohammed,Shivkumar Chandrasekaran,B.S. Manjunath +5 more
TL;DR: A novel approach to detect, attribute and localize GAN generated images that combines image features with deep learning methods is proposed.
Posted Content
Fast and Provable ADMM for Learning with Generative Priors
TL;DR: This work proposes a (linearized) Alternating Direction Method-of-Multipliers (ADMM) algorithm for minimizing a convex function subject to a nonconvex constraint, which can efficiently handle non-smooth objectives as well as exploit efficient partial minimization procedures, thus being faster in many practical scenarios.
Book ChapterDOI
W-Net : One-Shot Arbitrary-Style Chinese Character Generation with Deep Neural Networks
TL;DR: An efficient and generalized deep framework, namely, the W-Net, is introduced for the one-shot arbitrary-style Chinese character generation task, capable of learning and generating any arbitrary characters sharing the style similar to the given single character.
Proceedings ArticleDOI
Control-Theoretic Analysis of Smoothness for Stability-Certified Reinforcement Learning
Ming Jin,Javad Lavaei +1 more
TL;DR: Numerical evaluation on nonlinear and decentralized frequency control for large-scale power grids demonstrates that the smoothness margin can certify stability during both exploration and deployment for (deep) neural-network policies, which substantially surpass nominal controllers in performance.
Journal ArticleDOI
Adversarial Balancing-based Representation Learning for Causal Effect Inference with Observational Data
TL;DR: Adversarial Balancing-based representation learning for Causal Effect Inference (ABCEI) uses adversarial learning to balance the distributions of treatment and control group in the latent representation space, without any assumption on the form of the treatment selection/assignment function.
References
More filters
Dissertation
Learning Multiple Layers of Features from Tiny Images
TL;DR: In this paper, the authors describe how to train a multi-layer generative model of natural images, using a dataset of millions of tiny colour images, described in the next section.
Journal ArticleDOI
Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
TL;DR: This article presents a general class of associative reinforcement learning algorithms for connectionist networks containing stochastic units that are shown to make weight adjustments in a direction that lies along the gradient of expected reinforcement in both immediate-reinforcement tasks and certain limited forms of delayed-reInforcement tasks, and they do this without explicitly computing gradient estimates.
Posted Content
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
TL;DR: This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning.
Posted Content
Improved Techniques for Training GANs
TL;DR: In this article, the authors present a variety of new architectural features and training procedures that apply to the generative adversarial networks (GANs) framework and achieve state-of-the-art results in semi-supervised classification on MNIST, CIFAR-10 and SVHN.
Proceedings Article
Categorical Reparameterization with Gumbel-Softmax
Eric Jang,Shixiang Gu,Ben Poole +2 more
TL;DR: Gumbel-Softmax as mentioned in this paper replaces the non-differentiable samples from a categorical distribution with a differentiable sample from a novel Gumbel softmax distribution, which has the essential property that it can be smoothly annealed into the categorical distributions.