results for au:Wen_L in:cs

- Nov 21 2017 cs.CV arXiv:1711.06897v2For object detection, the two-stage approach (e.g., Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (e.g., SSD) has the advantage of high efficiency. To inherit the merits of both while overcoming their disadvantages, in this paper, we propose a novel single-shot based detector, called RefineDet, that achieves better accuracy than two-stage methods and maintains comparable efficiency of one-stage methods. RefineDet consists of two inter-connected modules, namely, the anchor refinement module and the object detection module. Specifically, the former aims to (1) filter out negative anchors to reduce search space for the classifier, and (2) coarsely adjust the locations and sizes of anchors to provide better initialization for the subsequent regressor. The latter module takes the refined anchors as the input from the former to further improve the regression and predict multi-class label. Meanwhile, we design a transfer connection block to transfer the features in the anchor refinement module to predict locations, sizes and class labels of objects in the object detection module. The multi-task loss function enables us to train the whole network in an end-to-end way. Extensive experiments on PASCAL VOC 2007, PASCAL VOC 2012, and MS COCO demonstrate that RefineDet achieves state-of-the-art detection accuracy with high efficiency. Code is available at https://github.com/sfzhang15/RefineDet .
- Jul 13 2017 cs.CR arXiv:1707.03611v1This paper is devoted to measuring the security of cyber networks under advanced persistent threats (APTs). First, an APT-based cyber attack-defense process is modeled as an individual-level dynamical system. Second, the dynamic model is shown to exhibit the global stability. On this basis, a new security metric of cyber networks, which is known as the limit security, is defined as the limit expected fraction of compromised nodes in the networks. Next, the influence of different factors on the limit security is illuminated through theoretical analysis and computer simulation. This work helps understand the security of cyber networks under APTs.
- Jul 11 2017 cs.CR arXiv:1707.02437v1To achieve an intended objective, an adversary may conduct an advanced persistent threat (APT) campaign against a targeted cyber network. Before an APT attack is launched, the attacker must maximize the effectiveness of the attack by properly allocating available APT resource. This paper addresses the APT effectiveness maximization problem. First, an APT-related cyber attack-defense process is modeled as an individual-level dynamical system, and the APT effectiveness maximization problem is modeled as a constrained optimization problem. Second, a type of good APT resource allocation schemes, which are known as Genetic-Algorithm-Based (GAB) schemes, are derived by solving the established optimization problem with a well-designed genetic algorithm. Next, the influences of different factors, including the available APT resource per unit time, the attack duration and the network heterogeneity, on the cost effectiveness of a GAB scheme are concluded through computer simulations. Finally, five types of heuristic APT resource allocation schemes are considered, and an experimental comparison among the cost effectiveness of these schemes and GAB schemes is conducted. This work helps understand the pros and cons of APTs.
- Jun 14 2017 cs.CV arXiv:1706.03875v1Inconsistency in contrast enhancement can be used to expose image forgeries. In this work, we describe a new method to estimate contrast enhancement from a single image. Our method takes advantage of the nature of contrast enhancement as a mapping between pixel values, and the distinct characteristics it introduces to the image pixel histogram. Our method recovers the original pixel histogram and the contrast enhancement simultaneously from a single image with an iterative algorithm. Unlike previous methods, our method is robust in the presence of additive noise perturbations that are used to hide the traces of contrast enhancement. Furthermore, we also develop an e effective method to to detect image regions undergone contrast enhancement transformations that are different from the rest of the image, and use this method to detect composite images. We perform extensive experimental evaluations to demonstrate the efficacy and efficiency of our method method.
- Feb 09 2017 astro-ph.IM cs.DC arXiv:1702.02256v1Low-latency detections of gravitational waves (GWs) are crucial to enable prompt follow-up observations to astrophysical transients by conventional telescopes. We have developed a low-latency pipeline using a technique called Summed Parallel Infinite Impulse Response (SPIIR) filtering, realized by a Graphic Processing Unit (GPU). In this paper, we exploit the new \textitMaxwell memory access architecture in NVIDIA GPUs, namely the read-only data cache, warp-shuffle, and cross-warp atomic techniques. We report a 3-fold speed-up over our previous implementation of this filtering technique. To tackle SPIIR with relatively few filters, we develop a new GPU thread configuration with a nearly 10-fold speedup. In addition, we implement a multi-rate scheme of SPIIR filtering using Maxwell GPUs. We achieve more than 100-fold speed-up over a single core CPU for the multi-rate filtering scheme. This results in an overall of 21-fold CPU usage reduction for the entire SPIIR pipeline.
- May 20 2016 cs.CV arXiv:1605.05829v1Spectral-spatial processing has been increasingly explored in remote sensing hyperspectral image classification. While extensive studies have focused on developing methods to improve the classification accuracy, experimental setting and design for method evaluation have drawn little attention. In the scope of supervised classification, we find that traditional experimental designs for spectral processing are often improperly used in the spectral-spatial processing context, leading to unfair or biased performance evaluation. This is especially the case when training and testing samples are randomly drawn from the same image - a practice that has been commonly adopted in the experiments. Under such setting, the dependence caused by overlap between the training and testing samples may be artificially enhanced by some spatial information processing methods such as spatial filtering and morphological operation. Such interaction between training and testing sets has violated data independence assumption that is abided by supervised learning theory and performance evaluation mechanism. Therefore, the widely adopted pixel-based random sampling strategy is not always suitable to evaluate spectral-spatial classification algorithms because it is difficult to determine whether the improvement of classification accuracy is caused by incorporating spatial information into classifier or by increasing the overlap between training and testing samples. To partially solve this problem, we propose a novel controlled random sampling strategy for spectral-spatial methods. It can greatly reduce the overlap between training and testing samples and provides more objective and accurate evaluation.
- Mar 21 2016 cs.CV arXiv:1603.05930v1Graph based representation is widely used in visual tracking field by finding correct correspondences between target parts in consecutive frames. However, most graph based trackers consider pairwise geometric relations between local parts. They do not make full use of the target's intrinsic structure, thereby making the representation easily disturbed by errors in pairwise affinities when large deformation and occlusion occur. In this paper, we propose a geometric hypergraph learning based tracking method, which fully exploits high-order geometric relations among multiple correspondences of parts in consecutive frames. Then visual tracking is formulated as the mode-seeking problem on the hypergraph in which vertices represent correspondence hypotheses and hyperedges describe high-order geometric relations. Besides, a confidence-aware sampling method is developed to select representative vertices and hyperedges to construct the geometric hypergraph for more robustness and scalability. The experiments are carried out on two challenging datasets (VOT2014 and Deform-SOT) to demonstrate that the proposed method performs favorable against other existing trackers.
- This paper reviews gravitational wave sources and their detection. One of the most exciting potential sources of gravitational waves are coalescing binary black hole systems. They can occur on all mass scales and be formed in numerous ways, many of which are not understood. They are generally invisible in electromagnetic waves, and they provide opportunities for deep investigation of Einstein's general theory of relativity. Sect. 1 of this paper considers ways that binary black holes can be created in the universe, and includes the prediction that binary black hole coalescence events are likely to be the first gravitational wave sources to be detected. The next parts of this paper address the detection of chirp waveforms from coalescence events in noisy data. Such analysis is computationally intensive. Sect. 2 reviews a new and powerful method of signal detection based on the GPU-implemented summed parallel infinite impulse response filters. Such filters are intrinsically real time alorithms, that can be used to rapidly detect and localise signals. Sect. 3 of the paper reviews the use of GPU processors for rapid searching for gravitational wave bursts that can arise from black hole births and coalescences. In sect. 4 the use of GPU processors to enable fast efficient statistical significance testing of gravitational wave event candidates is reviewed. Sect. 5 of this paper addresses the method of multimessenger astronomy where the discovery of electromagnetic counterparts of gravitational wave events can be used to identify sources, understand their nature and obtain much greater science outcomes from each identified event.
- Dec 02 2015 cs.OH arXiv:1512.00428v3An increasing number of works have devoted to the application of Transition Adjacency Relation (TAR) as a means to capture behavioral features of business process models. In this paper, we systematically study the efficient TAR derivation from process models using unfolding technique which previously has been used to address the state space explosion when dealing with concurrent behaviors of a Petri net. We reveal and formally describe the equivalence between TAR and Event Adjacency Relation (EAR), the manifestation of TAR in the Complete Prefix Unfolding (CPU) of a Petri net. By computing TARs from CPU using this equivalence, we can alleviate the concurrency caused state-explosion issues. Furthermore, structural boosting rules are categorized, proved and added to the TAR computing algorithm. Formal proofs of correctness and generality of CPU-based TAR computation are provided for the first time by this work, and they significantly expand the range of Petri nets from which TARs can be efficiently derived. Experiments on both industrial and synthesized process models show the effectiveness of proposed CPU-based algorithms as well as the observation that they scale well with the increase in size and concurrency of business process models.
- Nov 16 2015 cs.CV arXiv:1511.04136v3In recent years, numerous effective multi-object tracking (MOT) methods are developed because of the wide range of applications. Existing performance evaluations of MOT methods usually separate the object tracking step from the object detection step by using the same fixed object detection results for comparisons. In this work, we perform a comprehensive quantitative study on the effects of object detection accuracy to the overall MOT performance, using the new large-scale University at Albany DETection and tRACking (UA-DETRAC) benchmark dataset. The UA-DETRAC benchmark dataset consists of 100 challenging video sequences captured from real-world traffic scenes (over 140,000 frames with rich annotations, including occlusion, weather, vehicle category, truncation, and vehicle bounding boxes) for object detection, object tracking and MOT system. We evaluate complete MOT systems constructed from combinations of state-of-the-art object detection and object tracking methods. Our analysis shows the complex effects of object detection accuracy on MOT system performance. Based on these observations, we propose new evaluation tools and metrics for MOT systems that consider both object detection and object tracking for comprehensive analysis.
- Apr 28 2015 cs.AI arXiv:1504.06700v1Multi-context systems (MCS) presented by Brewka and Eiter can be considered as a promising way to interlink decentralized and heterogeneous knowledge contexts. In this paper, we propose preferential multi-context systems (PMCS), which provide a framework for incorporating a total preorder relation over contexts in a multi-context system. In a given PMCS, its contexts are divided into several parts according to the total preorder relation over them, moreover, only information flows from a context to ones of the same part or less preferred parts are allowed to occur. As such, the first $l$ preferred parts of an PMCS always fully capture the information exchange between contexts of these parts, and then compose another meaningful PMCS, termed the $l$-section of that PMCS. We generalize the equilibrium semantics for an MCS to the (maximal) $l_{\leq}$-equilibrium which represents belief states at least acceptable for the $l$-section of an PMCS. We also investigate inconsistency analysis in PMCS and related computational complexity issues.
- Jun 25 2014 cs.AI arXiv:1406.6102v1This paper proposes a model, the linear model, for randomly generating logic programs with low density of rules and investigates statistical properties of such random logic programs. It is mathematically shown that the average number of answer sets for a random program converges to a constant when the number of atoms approaches infinity. Several experimental results are also reported, which justify the suitability of the linear model. It is also experimentally shown that, under this model, the size distribution of answer sets for random programs tends to a normal distribution when the number of atoms is sufficiently large.
- Mar 20 2014 cs.NA arXiv:1403.4747v1A highly efficient fast boundary element method (BEM) for solving large-scale engineering acoustic problems in a broad frequency range is developed and implemented. The acoustic problems are modeled by the Burton-Miller boundary integral equation (BIE), thus the fictitious frequency issue is completely avoided. The BIE is discretized by using the collocation method with piecewise constant elements. The linear systems are solved iteratively and accelerated by using a newly developed kernel-independent wideband fast directional algorithm (FDA) for fast summation of oscillatory kernels. In addition, the computational efficiency of the FDA is further promoted by exploiting the low-rank features of the translation matrices. The high accuracy and nearly linear computational complexity of the present method are clearly demonstrated by typical examples. An acoustic scattering problem with dimensionless wave number $kD$ (where $k$ is the wave number and $D$ is the typical length of the obstacle) up to 1000 and the degrees of freedom up to 4 million is successfully solved within 4 hours on a computer with one core and the memory usage is 24.7 GB.
- Jan 22 2014 cs.SE arXiv:1401.5198v1Behavior Engineering (BE) provides a rigorous way to derive a formal specification of a software system from the requirements written in natural language. Its graphical specification language, Behavior Tree (BT), has been used with success in industry to systematically translate large, complex, and often erroneous requirements into an integrated model of the software system. BE's process, the Behavior Modeling Process (BMP), allows requirements to be translated into individual requirement BTs one at a time, which are then integrated to form a holistic view of the system. The integrated BT then goes through a series of modifications to construct a specification BT, which is used for validation and verification. The BMP also addresses different types of defects in the requirements throughout its process. However, BT itself is a graphical modeling notation, and the types of integration relations, how they correspond to particular issues, how they should be integrated and how to get formal specification have not been clearly defined. As a result, the BMP is informal, and provides guidelines to perform all these tasks on an ad-hoc basis. In this paper, we first introduce a mathematical framework which defines the graphical form of BTs which we use to define the integration relationships of BTs and to formalize the integration strategy of the BMP. We then formulate semi-automated requirements defects detection techniques by utilizing this underlying mathematical framework, which may be extended to formalize the BMP, develop change management framework for it, build techniques for round-trip engineering and so on.
- Nov 19 2013 cs.NA arXiv:1311.5202v2In this paper, a highly efficient fast boundary element method (BEM) for solving large-scale engineering acoustic problems in a broad frequency range is developed and implemented. The acoustic problems are modeled by the Burton-Miller boundary integral equation (BIE), thus the fictitious frequency issue is completely avoided. The BIE is discretized by using the Nyström method based on the curved quadratic elements, leading to simple numerical implementation (no edge or corner problems) and high accuracy in the BEM analysis. The linear systems are solved iteratively and accelerated by using a newly developed kernel-independent wideband fast directional algorithm (FDA) for fast summation of oscillatory kernels. In addition, the computational efficiency of the FDA is further promoted by exploiting the low-rank features of the translation matrices, resulting in two- to three-fold reduction in the computational time of the multipole-to-local translations. The high accuracy and nearly linear computational complexity of the present method are clearly demonstrated by typical examples. An acoustic scattering problem with dimensionless wave number $kD$ (where $k$ is the wave number and $D$ is the typical length of the obstacle) up to 1000 and the degrees of freedom up to 4 million is successfully solved within 10 hours on a computer with one core and the memory usage is 24 GB.
- The polar coordinate transformation (PCT) method has been extensively used to treat various singular integrals in the boundary element method (BEM). However, the resultant integrands of the PCT tend to become nearly singular when (1) the aspect ratio of the element is large or (2) the field point is closed to the element boundary; thus a large number of quadrature points are needed to achieve a relatively high accuracy. In this paper, the first problem is circumvented by using a conformal transformation so that the geometry of the curved physical element is preserved in the transformed domain. The second problem is alleviated by using a sigmoidal transformation, which makes the quadrature points more concentrated around the near singularity. By combining the proposed two transformations with the Guiggiani's method in [M. Guiggiani, \emphet al. A general algorithm for the numerical solution of hypersingular boundary integral equations. \emphASME Journal of Applied Mechanics, 59(1992), 604-614], one obtains an efficient and robust numerical method for computing the weakly-, strongly- and hyper-singular integrals in high-order BEM with curved elements. Numerical integration results show that, compared with the original PCT, the present method can reduce the number of quadrature points considerably, for given accuracy. For further verification, the method is incorporated into a 2-order Nyström BEM code for solving acoustic Burton-Miller boundary integral equation. It is shown that the method can retain the convergence rate of the BEM with much less quadrature points than the existing PCT. The method is implemented in C language and freely available.
- Dec 14 2012 cs.CE physics.comp-ph arXiv:1212.3032v2The frequency-domain fast boundary element method (BEM) combined with the exponential window technique leads to an efficient yet simple method for elastodynamic analysis. In this paper, the efficiency of this method is further enhanced by three strategies. Firstly, we propose to use exponential window with large damping parameter to improve the conditioning of the BEM matrices. Secondly, the frequency domain windowing technique is introduced to alleviate the severe Gibbs oscillations in time-domain responses caused by large damping parameters. Thirdly, a solution extrapolation scheme is applied to obtain better initial guesses for solving the sequential linear systems in the frequency domain. Numerical results of three typical examples with the problem size up to 0.7 million unknowns clearly show that the first and third strategies can significantly reduce the computational time. The second strategy can effectively eliminate the Gibbs oscillations and result in accurate time-domain responses.
- The kernel-independent fast multipole method (KIFMM) proposed in [1] is of almost linear complexity. In the original KIFMM the time-consuming M2L translations are accelerated by FFT. However, when more equivalent points are used to achieve higher accuracy, the efficiency of the FFT approach tends to be lower because more auxiliary volume grid points have to be added. In this paper, all the translations of the KIFMM are accelerated by using the singular value decomposition (SVD) based on the low-rank property of the translating matrices. The acceleration of M2L is realized by first transforming the associated translating matrices into more compact form, and then using low-rank approximations. By using the transform matrices for M2L, the orders of the translating matrices in upward and downward passes are also reduced. The improved KIFMM is then applied to accelerate BEM. The performance of the proposed algorithms are demonstrated by three examples. Numerical results show that, compared with the original KIFMM, the present method can reduce about 40% of the iterating time and 25% of the memory requirement.