Related papers: A novel guided deep learning algorithm to design l…

Determinantal point processes (DPPs) have attracted significant attention in machine learning for their ability to model subsets drawn from a large item collection. Recent work shows that nonsymmetric DPP (NDPP) kernels have significant…

Commercial iterative reconstruction techniques on modern CT scanners target radiation dose reduction but there are lingering concerns over their impact on image appearance and low contrast detectability. Recently, machine learning,…

Halftoning aims to reproduce a continuous-tone image with pixels whose intensities are constrained to two discrete levels. This technique has been deployed on every printer, and the majority of them adopt fast methods (e.g., ordered…

Plasmonics is based on surface plasmon polariton (SPP) modes which can be laterally confined below the diffraction limit, thereby enabling ultracompact optical components. In order to exploit this potential, the fundamental bottleneck of…

By using numerical and analytical methods, we describe the generation of fine-scale lateral electromagnetic waves, called surface plasmon-polaritons (SPPs), on atomically thick, metamaterial conducting sheets in two spatial dimensions (2D).…

Due to its capability to identify erroneous disparity assignments in dense stereo matching, confidence estimation is beneficial for a wide range of applications, e.g. autonomous driving, which needs a high degree of confidence as mandatory…

Convolutional neural networks (CNNs) have made resounding success in many computer vision tasks such as image classification and object detection. However, their performance degrades rapidly on tougher tasks where images are of low…

Machine learning, especially deep learning, is dramatically changing the methods associated with optical thin-film inverse design. The vast majority of this research has focused on the parameter optimization (layer thickness, and structure…

We propose to focus on the problem of discovering neural network architectures efficient in terms of both prediction quality and cost. For instance, our approach is able to solve the following tasks: learn a neural network able to predict…

High-throughput virtual screening is an indispensable technique utilized in the discovery of small molecules. In cases where the library of molecules is exceedingly large, the cost of an exhaustive virtual screen may be prohibitive.…

The design of metamaterials which support unique optical responses is the basis for most thin-film nanophotonics applications. In practice this inverse design problem can be difficult to solve systematically due to the large design…

Transformation optics has recently attracted extensive interest, since it provides a novel design methodology for manipulating light at will. Although transformation optics in principle embraces all forms of electromagnetic phenomena on all…

Recently, guiding electromagnetic surface waves without sacrificing scattering losses through paths that have arbitrary shape bumps has gained a lot of interest due to its wealth of advantages in modern photonics and plasmonics devices. In…

Biomimetic nanoengineered metamaterials called chiral sculptured thin films (CSTFs) are attractive platforms for optical sensing because their porosity, morphology and optical properties can be tailored to order. Furthermore, their ability…

Blind inpainting algorithms based on deep learning architectures have shown a remarkable performance in recent years, typically outperforming model-based methods both in terms of image quality and run time. However, neural network…

In SAR domain many application like classification, detection and segmentation are impaired by speckle. Hence, despeckling of SAR images is the key for scene understanding. Usually despeckling filters face the trade-off of speckle…

This paper proposed a Soft Filter Pruning (SFP) method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Specifically, the proposed SFP enables the pruned filters to be updated when training the model after…

The ability to tailor the porosity and optical properties of columnar thin films (CTFs) renders them promising platforms for optical sensing. In particular, surface-plasmon-polariton (SPP) waves, guided by the planar interface of an…

Determinantal point processes (DPPs) have garnered attention as an elegant probabilistic model of set diversity. They are useful for a number of subset selection tasks, including product recommendation. DPPs are parametrized by a positive…

The recent surge in Deep Learning (DL) research of the past decade has successfully provided solutions to many difficult problems. The field of quantitative analysis has been slowly adapting the new methods to its problems, but due to…