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
Joint 3D Tracking and Forecasting with Graph Neural Network and Diversity Sampling
TL;DR: This work proposes a unified solution for 3D MOT and trajectory forecasting which also incorporates two additional novel computational units and introduces Graph Neural Networks to capture the way in which multiple agents interact with one another.
Proceedings ArticleDOI
A Decoupled 3D Facial Shape Model by Adversarial Training
TL;DR: This work introduces a novel architecture that combines a 3D generator with a 2D discriminator that leverages conventional CNNs and presents a training scheme, based on auxiliary classifiers, to explicitly disentangle identity and expression attributes.
Posted Content
Quick and Easy Time Series Generation with Established Image-based GANs.
TL;DR: This work implements Wasserstein GANs (WGANs) with gradient penalty due to their stability in training to synthesise three different types of data; sinusoidal data, photoplethysmograph (PPG) data and electrocardiograph (ECG) data.
Journal ArticleDOI
On deep-learning-based geometric filtering in aerodynamic shape optimization
Jichao Li,Mengqi Zhang +1 more
TL;DR: This work finds that using the geometric filtering with a lower bound of ∼0.7 does not exclude innovative aerodynamic shapes that maximize cruise efficiency, and two applications of geometric filtering in aerodynamic shape optimization are showcased: the geometric validity constraint and global modal shape derivation.
Journal ArticleDOI
A Novel Approach to Data Augmentation for Pavement Distress Segmentation
TL;DR: It is shown how, starting from few labeled images, it is possible to augment small and long-tail datasets by producing new images with the associated semantic layouts and a remarkable increase in performance, especially with low cardinality classes, when CNNs are trained on the augmented datasets with respect to original datasets.
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.