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
Proceedings Article
Symbolic music generation with transformer-GANs
Aashiq Muhamed,Liang Li,Xingjian Shi,Suri Yaddanapudi,Wayne Chi,Dylan Jackson,Rahul Suresh,Zachary C. Lipton,Alexander J. Smola +8 more
TL;DR: It is demonstrated via human evaluations and a new discriminative metric that the music generated by the approach outperforms a baseline trained with likelihood maximization, the state-of-the-art Music Transformer, and other GANs used for sequence generation.
Proceedings Article
Robust Subspace Recovery Layer for Unsupervised Anomaly Detection
TL;DR: A neural network for unsupervised anomaly detection with a novel robust subspace recovery layer (RSR layer) that seeks to extract the underlying subspace from a latent representation of the given data and removes outliers that lie away from this subspace.
Proceedings Article
Real or Not Real, that is the Question
TL;DR: This paper generalizes the standard GAN to a new perspective by treating realness as a random variable that can be estimated from multiple angles, referred to as RealnessGAN, which enables the basic DCGAN architecture to generate realistic images at 1024*1024 resolution when trained from scratch.
Proceedings ArticleDOI
Data-Driven Maneuver Modeling using Generative Adversarial Networks and Variational Autoencoders for Safety Validation of Highly Automated Vehicles
TL;DR: The results show that the networks learn to describe lane change maneuvers by up to four intuitive parameters, and are able to map existing lane change trajectories to values of the learned parameters and generate new, previously unseen, realistic trajectories.
Posted Content
Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions
TL;DR: This study proposes a novel parameter-free algorithm for learning the underlying distributions of complicated datasets and sampling from them based on a functional optimization problem, which aims at finding a measure that is close to the data distribution as much as possible and also expressive enough for generative modeling purposes.
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.