The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
One of recent trends [31, 32, 14] in network architecture design is stacking small filters (e.g., 1x1 or 3x3) in the entire network because the stacked small filters is more efficient than a large kernel, given the same computational complexity. However, in the field of semantic segmentation, where we need to perform dense per-pixel prediction, we find that the large kernel (and effective receptive...
This paper presents an efficient methodology for approximating kernel functions in Gaussian process classification (GPC). Two models are introduced. We first include the standard random Fourier features (RFF) approximation into GPC, which largely improves the computational efficiency and permits large scale remote sensing data classification. In addition, we develop a novel approach which avoids randomly...
The authors propose a variational level set image segmentation method for intensity inhomogeneous texture image. The method first extracts the main image structure by a relative total variation image decomposition method, which can better decompose the image into structural and textural parts. Then only uses the structural part as the input image for the variational level set segmentation. The intensity...
This paper considers the modelling of scalar fields exhibiting non-stationary noise in the context of Gaussian Process (GP) regression. We show how a Heteroscedastic GP produces more accurate predictions of the variance of a process of this type compared to the standard Homoscedastic model. We present a parametric model for the noise process and derive analytical solutions to the Log Marginal Likelihood...
In this paper, we study the effects of using smoothed variance estimates in place of the sample variances on the performance of stochastic kriging (SK). Different variance estimation methods are investigated and it is shown through numerical examples that such a replacement leads to improved predictive performance of SK. An SK-based dual metamodeling approach is further proposed to obtain an efficient...
The details of oriented visual stimuli are better resolved when they are horizontal or vertical rather than oblique. This "oblique effect" has been researched and confirmed in numerous research studies, including behavioral studies and neurophysiological and neuroimaging findings. Although the "oblique effect" has influence in many fields, little research integrated it into computational...
Kriging-based Global optimization has been proposed and extensively used for solving black-box optimization problems with expensive function evaluations. The performance of such algorithm relies heavily on the effectiveness of the infill criterion that is used to decide which point to evaluate next. Two common infill criteria are, the probability of improvement (PI) and the expected improvement (EI)...
We present a model for time series consisting of an infinite mixture of basis functions, whereby the bases and the mixing process are modelled as posterior means of latent Gaussian processes (GPs). Conditional to observed data, the bases and the mixing process are learnt using a parametric approximation based on pseudo-observations, where the complexity and accuracy of the method are controlled by...
Many background subtraction algorithms have been proposed in the last fifteen years and an important issue is to provide a way to evaluate and compare most popular models according to criteria. This paper present a comparison among the eleven models using BMC dataset and give a guideline to choose different algorithms in different scenes by computing the F-measure, Peak Signal-Noise Ratio, Structural...
The article presents a security solution of mapping RBAC model in to Linux kernel systems. RBAC management model represents an effective concept of mapping user organization structure to access control of computer systems objects. Definition of RBAC model roles allows declaring permitted operations with specified security policy. Based on the roles, system management model provides a comprehensive...
Custom hardware accelerators are widely used to improve the performance of software applications in terms of execution times and to reduce energy consumption. However the realization of an hardware accelerator and its integration in the final system is a difficult and error prone task. For this reason, both Industry and Academy are continuously developing Computer Aided Design (CAD) tools to assist...
Accurate forecasts of future climate with numerical models of atmosphere and ocean are of vital importance. However, forecast quality is often limited by the available computational power. This paper investigates the acceleration of a C-grid shallow water model through the use of reduced precision targeting FPGA technology. Using a double-gyre scenario, we show that the mantissa length of variables...
In the last decade, OpenCL has sparked the interest of the computing world as it is a language based on an open standard that can run on many different heterogeneous platforms. This standard is continuously evolving to adapt to various use cases of different platforms. For example, with requests from the FPGA community, the pipe construct was added to the standard to facilitate the implementation...
This paper introduces a novel method to conserve the shape of smoke simulation based on fast Fourier transform. Through the advection step of simulating Navier-Stokes equation, semi-Lagrange method loses the high frequency part of fluid, since the interpolation method is equal to low-pass filter, which causes the shape of fluids variable in different resolution. The method consists of the dissipation...
In this paper, we introduce a novel technique of deriving Fisher kernels from the Gaussian Bernoulli restricted Boltzmann machine (GBRBM) and factored 3-way restricted Boltzmann machine (FRBM) to yield better texture classification results. GBRBM and FRBM, both, are stochastic probabilistic models that have already shown their suitability for modelling real valued continuous data, however, they are...
OpenCL is an open standard for programming of parallel heterogeneous systems. It is designed for portability, therefore being utilized in the area of embedded system programming as well as high performance computing (HPC). Due to the applicability on different platforms, OpenCL library vendors have a certain freedom in implementing parts of the OpenCL execution model. Multiple versions of the standard...
Model scoring in latent factor models is essential for a broad spectrum of applications such as clustering, change point detection or model order estimation. In a Bayesian setting, model selection is achieved via computation of the marginal likelihood. However, this is a typically challenging task as it involves calculation of a multidimensional integral over all the latent variables. In this paper,...
This paper proposes a method to simultaneously select the most relevant single nucleotide polymorphisms (SNPs) markers — the attributes — for the characterization of any measurable phenotype described by a continuous variable using support vector regression (SVR) with Pearson VII Universal Kernel (PUK). The proposed study is multiattribute towards considering several markers simultaneously to explain...
In this paper, we report on the development of an efficient GPU implementation of the Strassen-Winograd matrix multiplication algorithm for matrices of arbitrary sizes. We utilize multi-kernel streaming to exploit concurrency across sub-matrix operations in addition to intra-operation parallelism. We evaluate the performance of the implementation in comparison with CUBLAS-5.0 on Fermi and Kepler GPUs...
Schruben (1983) developed standardized time series (STS) methods to construct confidence intervals (CIs) for the steady-state mean of a stationary process. STS techniques cancel out the variance constant in the asymptotic distribution of the centered and scaled estimator, thereby eliminating the need to consistently estimate the asymptotic variance to obtain a CI. This is desirable since estimating...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.