Related papers: DeepZipper: A Novel Deep Learning Architecture for…
Deep learning (DL) has been widely applied into hyperspectral image (HSI) classification owing to its promising feature learning and representation capabilities. However, limited by the spatial resolution of sensors, existing DL-based…
Remote sensing images pose distinct challenges for downstream tasks due to their inherent complexity. While a considerable amount of research has been dedicated to remote sensing classification, object detection and semantic segmentation,…
A deep neural network (DNN) model consisting of two hidden layers was proposed for predicting the immediate environments of specific atoms based on X-ray absorption near-edge spectra (XANES). The output layer of the DNN can be adjusted to…
Strongly lensed type Ia supernovae (SNe Ia) provide a unique cosmological probe to address the Hubble tension problem in cosmology. In addition to the sensitivity of the time delays to the value of the Hubble constant, the transient and…
Change detection of high-resolution remote sensing images is an important task in earth observation and was extensively investigated. Recently, deep learning has shown to be very successful in plenty of remote sensing tasks. The current…
Basic considerations of lens detection and identification indicate that a wide field survey of the types planned for weak lensing and Type Ia SNe with SNAP are close to optimal for the optical detection of strong lenses. Such a…
In the coming LSST era, we will observe $\mathcal{O}(100)$ of lensed supernovae (SNe). In this paper, we investigate possibility for predicting time and sky position of a supernova using strong lensing. We find that it will be possible to…
To simplify the parameter of the deep learning network, a cascaded compressive sensing model "CSNet" is implemented for image classification. Firstly, we use cascaded compressive sensing network to learn feature from the data. Secondly,…
We introduce QuasarNET, a deep convolutional neural network that performs classification and redshift estimation of astrophysical spectra with human-expert accuracy. We pose these two tasks as a \emph{feature detection} problem: presence or…
Strong gravitationally lensed supernovae (SNe) are a powerful probe for cosmology and stellar physics. The relative time delays between lensed SN images provide an independent way of measuring a fundamental cosmological parameter -- the…
We apply deep recurrent neural networks, which are capable of learning complex sequential information, to classify supernovae\footnote{Code available at \href{https://github.com/adammoss/supernovae}{https://github.com/adammoss/supernovae}}.…
This paper proposes a new deep convolutional neural network (DCNN) architecture that learns pixel embeddings, such that pairwise distances between the embeddings can be used to infer whether or not the pixels lie on the same region. That…
Recent research on remote sensing object detection has largely focused on improving the representation of oriented bounding boxes but has overlooked the unique prior knowledge presented in remote sensing scenarios. Such prior knowledge can…
Forthcoming imaging surveys will potentially increase the number of known galaxy-scale strong lenses by several orders of magnitude. For this to happen, images of tens of millions of galaxies will have to be inspected to identify potential…
With several new large-scale surveys on the horizon, including LSST, TESS, ZTF, and Evryscope, faster and more accurate analysis methods will be required to adequately process the enormous amount of data produced. Deep learning, used in…
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we…
Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to…
Lensed supernovae (SNae) are among the most eagerly anticipated transients expected from the Legacy Survey of Space and Time (LSST). Quadruply lensed SNae permit more highly constrained models than "mere" doubles. The quadruply lensed SN…
Gravitationally lensed supernovae (glSNe) are of interest for time delay cosmology and SN physics. However, glSNe detections are rare, owing to the intrinsic rarity of SN explosions, the necessity of alignment with a foreground lens, and…
As gravitational wave (GW) catalogs continue to expand, exhaustive Bayesian comparisons of candidate event pairs become increasingly computationally expensive, which motivates the development of fast prescreening methods for strongly lensed…