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
Facial Age Synthesis With Label Distribution-Guided Generative Adversarial Network
TL;DR: This paper proposes label distribution-guided generative adversarial network (ldGAN), where each sample is associated with an age label distribution rather than a single age group, and demonstrates the effectiveness of ldGAN in both learning short-term aging patterns and coping with the lack of training data.
Posted Content
Learning Controllable Fair Representations
TL;DR: In this article, an information-theoretically motivated objective for learning maximally expressive representations subject to fairness constraints is proposed, which allows the user to control the fairness of the representations by specifying limits on unfairness.
Journal ArticleDOI
LDGAN: A Synthetic Aperture Radar Image Generation Method for Automatic Target Recognition
TL;DR: An entirely new loss function is defined for the LDGAN, which utilizes the Wasserstein distance to replace the original distance measurement of the conventional generative adversarial networks (GANs), thus efficiently avoiding the collapse mode problem.
Posted Content
Domain Generalization with Optimal Transport and Metric Learning.
TL;DR: This work tackles the domain generalization problem to learn from multiple source domains and generalize to a target domain with unknown statistics and adopts optimal transport with Wasserstein distance, which could constrain the class label similarity, for adversarial training and also further deploy a metric learning objective to leverage the label information for achieving distinguishable classification boundary.
Proceedings ArticleDOI
EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation
TL;DR: In this article, a bidirectional modality reconstruction (BMR) module is proposed to bridge both modalities and simultaneously exploit them to distill knowledge via the crafted pairs, causing no extra computation in the inference.
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.