Related papers: Deep Learning Unresolved Lensed Lightcurves

We propose a novel study of generating unseen arbitrary viewpoints for infrared imagery in the non-linear feature subspace . Current methods use synthetic images and often result in blurry and distorted outputs. Our approach on the contrary…

Deep neural networks as image priors have been recently introduced for problems such as denoising, super-resolution and inpainting with promising performance gains over hand-crafted image priors such as sparsity and low-rank. Unlike learned…

Radio source detection through conventional algorithms has been unreliable when trying to solve for large number of sources in the presence of low SINR and less number of snapshots. We address this by reformulating source detection as a…

Large-scale astronomical surveys have the potential to capture data on large numbers of strongly gravitationally lensed supernovae (LSNe). To facilitate timely analysis and spectroscopic follow-up before the supernova fades, an LSN needs to…

We propose a new sequential classification model for astronomical objects based on a recurrent convolutional neural network (RCNN) which uses sequences of images as inputs. This approach avoids the computation of light curves or difference…

Unsupervised learning of visual similarities is of paramount importance to computer vision, particularly due to lacking training data for fine-grained similarities. Deep learning of similarities is often based on relationships between pairs…

Employing deep neural networks as natural image priors to solve inverse problems either requires large amounts of data to sufficiently train expressive generative models or can succeed with no data via untrained neural networks. However,…

Exemplar learning of visual similarities in an unsupervised manner is a problem of paramount importance to Computer Vision. In this context, however, the recent breakthrough in deep learning could not yet unfold its full potential. With…

Astronomical surveys of celestial sources produce streams of noisy time series measuring flux versus time ("light curves"). Unlike in many other physical domains, however, large (and source-specific) temporal gaps in data arise naturally…

We investigate strongly gravitationally lensed type II supernovae (LSNe II) for time-delay cosmography incorporating microlensing effects, which expands on previous microlensing studies of type Ia supernovae (SNe Ia). We use the…

We present a novel deep convolutional neural network (DCNN) system for fine-grained image classification, called a mixture of DCNNs (MixDCNN). The fine-grained image classification problem is characterised by large intra-class variations…

Cadenced optical imaging surveys in the next decade will be capable of detecting time-varying galaxy-scale strong gravitational lenses in large numbers, increasing the size of the statistically well-defined samples of multiply-imaged…

The quality of microscopy images often suffers from optical aberrations. These aberrations and their associated point spread functions have to be quantitatively estimated to restore aberrated images. The recent state-of-the-art method…

Lensless microscopy with coherent or partially coherent light sources is a well known imaging technique, commonly referred as digital in-line holographic microscopy. In the established methods, both the spatial and temporal coherence of…

In the field of machine unlearning, certified unlearning has been extensively studied in convex machine learning models due to its high efficiency and strong theoretical guarantees. However, its application to deep neural networks (DNNs),…

The phenomenon of cosmic shear, or distortion of images of distant sources unaccompanied by magnification, is an effective way of probing the content and state of the foreground Universe, because light rays do not have to pass through mass…

The currently used linear and nonlinear lens inversion techniques are based on distortion estimators whose complicated source redshift dependence makes the influence of the redshift distribution of the sources difficult to take into account…

The gravitational field of a galaxy can act as a lens and deflect the light emitted by a more distant object such as a quasar. Strong gravitational lensing causes multiple images of the same quasar to appear in the sky. Since the light in…

We examine the ability of gravitational lens time delays to reveal complex structure in lens potentials. In Congdon, Keeton & Nordgren (2008), we predicted how the time delay between the bright pair of images in a "fold" lens scales with…

In visual recognition tasks, such as image classification, unsupervised learning exploits cheap unlabeled data and can help to solve these tasks more efficiently. We show that the recursive autoconvolution operator, adopted from physics,…