اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدParameterizing Region Covariance: An Efficient Way To Apply Sparse Codes On Second Order Statistics
53
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Sparse representations have been successfully applied to signal processing, computer vision and machine learning. Currently there is a trend to learn sparse models directly on structure data, such as region covariance. However, such methods when combined with region covariance often require complex computation. We present an approach to transform a structured sparse model learning problem to a traditional vectorized sparse modeling problem by constructing a Euclidean space representation for region covariance matrices. Our new representation has multiple advantages. Experiments on several vision tasks demonstrate competitive performance with the state-of-the-art methods.
قيم البحث
اقرأ أيضاً
Many large-scale machine learning problems involve estimating an unknown parameter $theta_{i}$ for each of many items. For example, a key problem in sponsored search is to estimate the click through rate (CTR) of each of billions of query-ad pairs. M
ost common methods, though, only give a point estimate of each $theta_{i}$. A posterior distribution for each $theta_{i}$ is usually more useful but harder to get. We present a simple post-processing technique that takes point estimates or scores $t_{i}$ (from any method) and estimates an approximate posterior for each $theta_{i}$. We build on the idea of calibration, a common post-processing technique that estimates $mathrm{E}left(theta_{i}!!bigm|!! t_{i}right)$. Our method, second order calibration, uses empirical Bayes methods to estimate the distribution of $theta_{i}!!bigm|!! t_{i}$ and uses the estimated distribution as an approximation to the posterior distribution of $theta_{i}$. We show that this can yield improved point estimates and useful accuracy estimates. The method scales to large problems - our motivating example is a CTR estimation problem involving tens of billions of query-ad pairs.
We investigate and derive second solutions to linear homogeneous second-order difference equations using a variety of methods, in each case going beyond the purely formal solution and giving explicit expressions for the second solution. We present a
new implementation of dAlemberts reduction of order method, applying it to linear second-order recursion equations. Further, we introduce an iterative method to obtain a general solution, giving two linearly independent polynomial solutions to the recurrence relation. In the case of a particular confluent hypergeometric function for which the standard second solution is not independent of the first, i.e. the solutions are degenerate, we use the corresponding differential equation and apply the extended Cauchy-integral method to find a polynomial second solution for the difference equation. We show that the standard dAlembert method also generates this polynomial solution.
Human eyes concentrate different facial regions during distinct cognitive activities. We study utilising facial visual saliency maps to classify different facial expressions into different emotions. Our results show that our novel method of merely us
ing facial saliency maps can achieve a descent accuracy of 65%, much higher than the chance level of $1/7$. Furthermore, our approach is of semi-supervision, i.e., our facial saliency maps are generated from a general saliency prediction algorithm that is not explicitly designed for face images. We also discovered that the classification accuracies of each emotional class using saliency maps demonstrate a strong positive correlation with the accuracies produced by face images. Our work implies that humans may look at different facial areas in order to perceive different emotions.
In the past years, significant improvements in the field of neural architecture search(NAS) have been made. However, it is still challenging to search for efficient networks due to the gap between the searched constraint and real inference time exist
s. To search for a high-performance network with low inference time, several previous works set a computational complexity constraint for the search algorithm. However, many factors affect the speed of inference(e.g., FLOPs, MACs). The correlation between a single indicator and the latency is not strong. Currently, some re-parameterization(Rep) techniques are proposed to convert multi-branch to single-path architecture which is inference-friendly. Nevertheless, multi-branch architectures are still human-defined and inefficient. In this work, we propose a new search space that is suitable for structural re-parameterization techniques. RepNAS, a one-stage NAS approach, is present to efficiently search the optimal diverse branch block(ODBB) for each layer under the branch number constraint. Our experimental results show the searched ODBB can easily surpass the manual diverse branch block(DBB) with efficient training. Code and models will be available sooner.
The method based on fast Fourier transforms proposed by G. Roman-Perez and J. M. Soler [Phys. Rev. Lett. 103, 096102 (2009)], which allows for a computationally fast implementation of the nonlocal van der Waals (vdW) functionals, has significantly co
ntributed to making the vdW functionals popular in solid-state physics. However, the Roman-Perez-Soler method relies on a plane-wave expansion of the electron density; therefore it can not be applied readily to all-electron densities for which an unaffordable number of plane waves would be required for an accurate expansion. In this work, we present the results for the lattice constant and binding energy of solids that were obtained by applying a smoothing procedure to the all-electron density calculated with the linearized augmented plane-wave method. The smoothing procedure has the advantages of being very simple to implement, basis-set independent, and allowing the calculation of the potential. It is also shown that the results agree very well with those from the literature that were obtained with the projector augmented wave method.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
