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
Feature Affinity-Based Pseudo Labeling for Semi-Supervised Person Re-Identification
TL;DR: Zhang et al. as mentioned in this paper proposed a novel feature affinity-based pseudo labeling method with two possible label encodings, which measured the affinity of unlabeled samples with the underlying clusters of labeled data samples using the intermediate feature representations from deep networks.
Posted Content
Generative Adversarial Networks for Financial Trading Strategies Fine-Tuning and Combination
TL;DR: This work proposes the use of Conditional Generative Adversarial Networks (cGANs) for trading strategy calibration and aggregation, and suggests that cGANs are a suitable alternative for strategy calibrated and combination, providing outperformance when the traditional techniques fail to generate any alpha.
Book ChapterDOI
High Quality Facial Surface and Texture Synthesis via Generative Adversarial Networks
TL;DR: A linear 3D morphable model for faces, which can be found at the core of many computer vision applications such as face reconstruction, recognition and authentication to name just a few.
Proceedings ArticleDOI
SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation
TL;DR: A novel method for combining synthetic and real images when training networks to determine geometric information from a single image is proposed, connected to a primary network for end-to-end training.
Journal ArticleDOI
Low-Dose CT Image Denoising Using a Generative Adversarial Network With a Hybrid Loss Function for Noise Learning
TL;DR: A noise learning generative adversarial network coupling with least squares, structural similarity and L1 losses for low-dose CT denoising, which can effectively suppress noise and remove artifacts compared with the state-of-the-art methods.
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.