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
CKD: Cross-Task Knowledge Distillation for Text-to-Image Synthesis
Mingkuan Yuan,Yuxin Peng +1 more
TL;DR: A multi-stage knowledge distillation paradigm to decompose the distillation process into multiple stages is designed, effective to approximate the distributions of real image and understand textual information for T2IS, which can improve the visual quality and semantic consistency of synthetic images.
Book ChapterDOI
Conditional Infilling GANs for Data Augmentation in Mammogram Classification
TL;DR: This work trains a class-conditional GAN to perform contextual in-filling, which is then used to synthesize lesions onto healthy screening mammograms and shows that GANs are capable of generating high-resolution synthetic mammogram patches.
Posted Content
Adversarial Sampling for Active Learning
Christoph Mayer,Radu Timofte +1 more
TL;DR: ASAL as mentioned in this paper is a GAN based active learning method that generates high entropy samples instead of directly annotating the synthetic samples, instead of searching similar samples from the pool and includes them for training, hence the quality of new samples is high and annotations are reliable.
Posted Content
Small Sample Learning in Big Data Era.
Jun Shu,Zongben Xu,Deyu Meng +2 more
TL;DR: A survey to comprehensively introduce the current techniques proposed on Small Sample Learning and some neuroscience evidences are provided to clarify the rationality of the entire SSL regime, and the relationship with human learning process.
Posted Content
Adversarial score matching and improved sampling for image generation
TL;DR: This work proposes two improvements to DSM-ALS: 1) Consistent Annealed Sampling as a more stable alternative to Annealed Langevin Sampling, and 2) a hybrid training formulation, composed of both Denoising Score Matching and adversarial objectives.
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.