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
Journal ArticleDOI
Spatio-temporal silhouette sequence reconstruction for gait recognition against occlusion
TL;DR: Wang et al. as discussed by the authors proposed silhouette sequence reconstruction from an occluded sequence (sVideo) based on a conditional deep generative adversarial network (GAN) and extracted the gait features from a one gait cycle image sequence.
Posted Content
Adversarial Lipschitz Regularization
TL;DR: It is shown that using an explicit Lipschitz penalty is indeed viable and leads to competitive performance when applied to Wasserstein GANs, highlighting an important connection between LipsChitz regularization and adversarial training.
Journal Article
AT-GAN: An Adversarial Generative Model for Non-constrained Adversarial Examples
TL;DR: This work proposes a novel attack framework called AT-GAN (Adversarial Transfer on Generative Adversarial Net), which first develops a normal GAN model to learn the distribution of benign data, and then transfers the pre-trained GANmodel to estimate the distributed distribution of adversarial examples for the target model.
Posted Content
Improved Bilevel Model: Fast and Optimal Algorithm with Theoretical Guarantee.
Junyi Li,Bin Gu,Heng Huang +2 more
TL;DR: This paper proposes an improved bilevel model which converges faster and better compared to the current formulation and provides theoretical guarantee and evaluation results over two tasks: Data Hyper-Cleaning and Hyper Representation Learning.
Posted Content
Multi-source Distilling Domain Adaptation
Sicheng Zhao,Guangzhi Wang,Shanghang Zhang,Yang Gu,Yaxian Li,Zhichao Song,Pengfei Xu,Runbo Hu,Hua Chai,Kurt Keutzer +9 more
TL;DR: This paper proposes a novel multi-source distilling domain adaptation (MDDA) network, which not only considers the different distances among multiple sources and the target, but also investigates the different similarities of the source samples to the target ones.
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.