Institution
Imperial College London
Education•London, Westminster, United Kingdom•
About: Imperial College London is a education organization based out in London, Westminster, United Kingdom. It is known for research contribution in the topics: Population & Medicine. The organization has 90019 authors who have published 209164 publications receiving 9337534 citations. The organization is also known as: Imperial College of Science, Technology and Medicine & Imperial College.
Topics: Population, Medicine, Context (language use), Cancer, Computer science
Papers published on a yearly basis
Papers
More filters
••
21 Jul 2017TL;DR: SRGAN as mentioned in this paper proposes a perceptual loss function which consists of an adversarial loss and a content loss, which pushes the solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images.
Abstract: Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large upscaling factors? The behavior of optimization-based super-resolution methods is principally driven by the choice of the objective function. Recent work has largely focused on minimizing the mean squared reconstruction error. The resulting estimates have high peak signal-to-noise ratios, but they are often lacking high-frequency details and are perceptually unsatisfying in the sense that they fail to match the fidelity expected at the higher resolution. In this paper, we present SRGAN, a generative adversarial network (GAN) for image super-resolution (SR). To our knowledge, it is the first framework capable of inferring photo-realistic natural images for 4x upscaling factors. To achieve this, we propose a perceptual loss function which consists of an adversarial loss and a content loss. The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images. In addition, we use a content loss motivated by perceptual similarity instead of similarity in pixel space. Our deep residual network is able to recover photo-realistic textures from heavily downsampled images on public benchmarks. An extensive mean-opinion-score (MOS) test shows hugely significant gains in perceptual quality using SRGAN. The MOS scores obtained with SRGAN are closer to those of the original high-resolution images than to those obtained with any state-of-the-art method.
6,884 citations
••
TL;DR: The results for 1990 and 2010 supersede all previously published Global Burden of Disease results and highlight the importance of understanding local burden of disease and setting goals and targets for the post-2015 agenda taking such patterns into account.
6,861 citations
••
TL;DR: This work describes here the first practical realization of a cloak of invisibility, constructed with the use of artificially structured metamaterials, designed for operation over a band of microwave frequencies.
Abstract: A recently published theory has suggested that a cloak of invisibility is in principle possible, at least over a narrow frequency band. We describe here the first practical realization of such a cloak; in our demonstration, a copper cylinder was "hidden" inside a cloak constructed according to the previous theoretical prescription. The cloak was constructed with the use of artificially structured metamaterials, designed for operation over a band of microwave frequencies. The cloak decreased scattering from the hidden object while at the same time reducing its shadow, so that the cloak and object combined began to resemble empty space.
6,830 citations
••
TL;DR: In this paper, three sampling-based approaches, namely stochastic substitution, the Gibbs sampler, and the sampling-importance-resampling algorithm, are compared and contrasted in relation to various joint probability structures frequently encountered in applications.
Abstract: Stochastic substitution, the Gibbs sampler, and the sampling-importance-resampling algorithm can be viewed as three alternative sampling- (or Monte Carlo-) based approaches to the calculation of numerical estimates of marginal probability distributions. The three approaches will be reviewed, compared, and contrasted in relation to various joint probability structures frequently encountered in applications. In particular, the relevance of the approaches to calculating Bayesian posterior densities for a variety of structured models will be discussed and illustrated.
6,294 citations
•
TL;DR: Stochastic substitution, the Gibbs sampler, and the sampling-importance-resampling algorithm can be viewed as three alternative sampling- (or Monte Carlo-) based approaches to the calculation of numerical estimates of marginal probability distributions.
Abstract: Stochastic substitution, the Gibbs sampler, and the sampling-importance-resampling algorithm can be viewed as three alternative sampling- (or Monte Carlo-) based approaches to the calculation of numerical estimates of marginal probability distributions. The three approaches will be reviewed, compared, and contrasted in relation to various joint probability structures frequently encountered in applications. In particular, the relevance of the approaches to calculating Bayesian posterior densities for a variety of structured models will be discussed and illustrated.
6,223 citations
Authors
Showing all 90798 results
Name | H-index | Papers | Citations |
---|---|---|---|
Albert Hofman | 267 | 2530 | 321405 |
David Miller | 203 | 2573 | 204840 |
Tamara B. Harris | 201 | 1143 | 163979 |
Mark I. McCarthy | 200 | 1028 | 187898 |
Peter J. Barnes | 194 | 1530 | 166618 |
Simon D. M. White | 189 | 795 | 231645 |
Patrick W. Serruys | 186 | 2427 | 173210 |
John Hardy | 177 | 1178 | 171694 |
Simon Baron-Cohen | 172 | 773 | 118071 |
Richard H. Friend | 169 | 1182 | 140032 |
Yang Gao | 168 | 2047 | 146301 |
Hongfang Liu | 166 | 2356 | 156290 |
Philippe Froguel | 166 | 820 | 118816 |
Salvador Moncada | 164 | 495 | 138030 |
Dennis R. Burton | 164 | 683 | 90959 |