July 29, 2019

3261 words 16 mins read

Paper Group ANR 94

Removal of Salt and Pepper noise from Gray-Scale and Color Images: An Adaptive Approach. Data Dependent Kernel Approximation using Pseudo Random Fourier Features. Temporal dynamics of semantic relations in word embeddings: an application to predicting armed conflict participants. Detecting Approximate Reflection Symmetry in a Point Set using Optimi …

Removal of Salt and Pepper noise from Gray-Scale and Color Images: An Adaptive Approach


Title	Removal of Salt and Pepper noise from Gray-Scale and Color Images: An Adaptive Approach
Authors	Sujaya Kumar Sathua, Arabinda Dash, Aishwaryarani Behera
Abstract	An efficient adaptive algorithm for the removal of Salt and Pepper noise from gray scale and color image is presented in this paper. In this proposed method first a 3X3 window is taken and the central pixel of the window is considered as the processing pixel. If the processing pixel is found as uncorrupted, then it is left unchanged. And if the processing pixel is found corrupted one, then the window size is increased according to the conditions given in the proposed algorithm. Finally the processing pixel or the central pixel is replaced by either the mean, median or trimmed value of the elements in the current window depending upon different conditions of the algorithm. The proposed algorithm efficiently removes noise at all densities with better Peak Signal to Noise Ratio (PSNR) and Image Enhancement Factor (IEF). The proposed algorithm is compared with different existing algorithms like MF, AMF, MDBUTMF, MDBPTGMF and AWMF.
Tasks	Image Enhancement
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02217v1
PDF	http://arxiv.org/pdf/1703.02217v1.pdf
PWC	https://paperswithcode.com/paper/removal-of-salt-and-pepper-noise-from-gray
Repo
Framework

Data Dependent Kernel Approximation using Pseudo Random Fourier Features


Title	Data Dependent Kernel Approximation using Pseudo Random Fourier Features
Authors	Bharath Bhushan Damodaran, Nicolas Courty, Philippe-Henri Gosselin
Abstract	Kernel methods are powerful and flexible approach to solve many problems in machine learning. Due to the pairwise evaluations in kernel methods, the complexity of kernel computation grows as the data size increases; thus the applicability of kernel methods is limited for large scale datasets. Random Fourier Features (RFF) has been proposed to scale the kernel method for solving large scale datasets by approximating kernel function using randomized Fourier features. While this method proved very popular, still it exists shortcomings to be effectively used. As RFF samples the randomized features from a distribution independent of training data, it requires sufficient large number of feature expansions to have similar performances to kernelized classifiers, and this is proportional to the number samples in the dataset. Thus, reducing the number of feature dimensions is necessary to effectively scale to large datasets. In this paper, we propose a kernel approximation method in a data dependent way, coined as Pseudo Random Fourier Features (PRFF) for reducing the number of feature dimensions and also to improve the prediction performance. The proposed approach is evaluated on classification and regression problems and compared with the RFF, orthogonal random features and Nystr{"o}m approach
Tasks
Published	2017-11-27
URL	http://arxiv.org/abs/1711.09783v1
PDF	http://arxiv.org/pdf/1711.09783v1.pdf
PWC	https://paperswithcode.com/paper/data-dependent-kernel-approximation-using
Repo
Framework

Temporal dynamics of semantic relations in word embeddings: an application to predicting armed conflict participants


Title	Temporal dynamics of semantic relations in word embeddings: an application to predicting armed conflict participants
Authors	Andrey Kutuzov, Erik Velldal, Lilja Øvrelid
Abstract	This paper deals with using word embedding models to trace the temporal dynamics of semantic relations between pairs of words. The set-up is similar to the well-known analogies task, but expanded with a time dimension. To this end, we apply incremental updating of the models with new training texts, including incremental vocabulary expansion, coupled with learned transformation matrices that let us map between members of the relation. The proposed approach is evaluated on the task of predicting insurgent armed groups based on geographical locations. The gold standard data for the time span 1994–2010 is extracted from the UCDP Armed Conflicts dataset. The results show that the method is feasible and outperforms the baselines, but also that important work still remains to be done.
Tasks	Word Embeddings
Published	2017-07-26
URL	http://arxiv.org/abs/1707.08660v1
PDF	http://arxiv.org/pdf/1707.08660v1.pdf
PWC	https://paperswithcode.com/paper/temporal-dynamics-of-semantic-relations-in
Repo
Framework

Detecting Approximate Reflection Symmetry in a Point Set using Optimization on Manifold


Title	Detecting Approximate Reflection Symmetry in a Point Set using Optimization on Manifold
Authors	Rajendra Nagar, Shanmuganathan Raman
Abstract	We propose an algorithm to detect approximate reflection symmetry present in a set of volumetrically distributed points belonging to $\mathbb{R}^d$ containing a distorted reflection symmetry pattern. We pose the problem of detecting approximate reflection symmetry as the problem of establishing correspondences between the points which are reflections of each other and we determine the reflection symmetry transformation. We formulate an optimization framework in which the problem of establishing the correspondences amounts to solving a linear assignment problem and the problem of determining the reflection symmetry transformation amounts to solving an optimization problem on a smooth Riemannian product manifold. The proposed approach estimates the symmetry from the geometry of the points and is descriptor independent. We evaluate the performance of the proposed approach on the standard benchmark dataset and achieve the state-of-the-art performance. We further show the robustness of our approach by varying the amount of distortion in a perfect reflection symmetry pattern where we perturb each point by a different amount of perturbation. We demonstrate the effectiveness of the method by applying it to the problem of 2-D and 3-D reflection symmetry detection along with comparisons.
Tasks
Published	2017-06-27
URL	http://arxiv.org/abs/1706.08801v6
PDF	http://arxiv.org/pdf/1706.08801v6.pdf
PWC	https://paperswithcode.com/paper/detecting-approximate-reflection-symmetry-in
Repo
Framework

Android Malware Detection using Deep Learning on API Method Sequences


Title	Android Malware Detection using Deep Learning on API Method Sequences
Authors	ElMouatez Billah Karbab, Mourad Debbabi, Abdelouahid Derhab, Djedjiga Mouheb
Abstract	Android OS experiences a blazing popularity since the last few years. This predominant platform has established itself not only in the mobile world but also in the Internet of Things (IoT) devices. This popularity, however, comes at the expense of security, as it has become a tempting target of malicious apps. Hence, there is an increasing need for sophisticated, automatic, and portable malware detection solutions. In this paper, we propose MalDozer, an automatic Android malware detection and family attribution framework that relies on sequences classification using deep learning techniques. Starting from the raw sequence of the app’s API method calls, MalDozer automatically extracts and learns the malicious and the benign patterns from the actual samples to detect Android malware. MalDozer can serve as a ubiquitous malware detection system that is not only deployed on servers, but also on mobile and even IoT devices. We evaluate MalDozer on multiple Android malware datasets ranging from 1K to 33K malware apps, and 38K benign apps. The results show that MalDozer can correctly detect malware and attribute them to their actual families with an F1-Score of 96%-99% and a false positive rate of 0.06%-2%, under all tested datasets and settings.
Tasks	Android Malware Detection, Malware Detection
Published	2017-12-25
URL	http://arxiv.org/abs/1712.08996v1
PDF	http://arxiv.org/pdf/1712.08996v1.pdf
PWC	https://paperswithcode.com/paper/android-malware-detection-using-deep-learning
Repo
Framework


Title	Temporal-related Convolutional-Restricted-Boltzmann-Machine capable of learning relational order via reinforcement learning procedure?
Authors	Zizhuang Wang
Abstract	In this article, we extend the conventional framework of convolutional-Restricted-Boltzmann-Machine to learn highly abstract features among abitrary number of time related input maps by constructing a layer of multiplicative units, which capture the relations among inputs. In many cases, more than two maps are strongly related, so it is wise to make multiplicative unit learn relations among more input maps, in other words, to find the optimal relational-order of each unit. In order to enable our machine to learn relational order, we developed a reinforcement-learning method whose optimality is proven to train the network.
Tasks
Published	2017-06-24
URL	http://arxiv.org/abs/1706.08001v1
PDF	http://arxiv.org/pdf/1706.08001v1.pdf
PWC	https://paperswithcode.com/paper/temporal-related-convolutional-restricted
Repo
Framework

Dataset Augmentation for Pose and Lighting Invariant Face Recognition


Title	Dataset Augmentation for Pose and Lighting Invariant Face Recognition
Authors	Daniel Crispell, Octavian Biris, Nate Crosswhite, Jeffrey Byrne, Joseph L. Mundy
Abstract	The performance of modern face recognition systems is a function of the dataset on which they are trained. Most datasets are largely biased toward “near-frontal” views with benign lighting conditions, negatively effecting recognition performance on images that do not meet these criteria. The proposed approach demonstrates how a baseline training set can be augmented to increase pose and lighting variability using semi-synthetic images with simulated pose and lighting conditions. The semi-synthetic images are generated using a fast and robust 3-d shape estimation and rendering pipeline which includes the full head and background. Various methods of incorporating the semi-synthetic renderings into the training procedure of a state of the art deep neural network-based recognition system without modifying the structure of the network itself are investigated. Quantitative results are presented on the challenging IJB-A identification dataset using a state of the art recognition pipeline as a baseline.
Tasks	Face Recognition
Published	2017-04-14
URL	http://arxiv.org/abs/1704.04326v1
PDF	http://arxiv.org/pdf/1704.04326v1.pdf
PWC	https://paperswithcode.com/paper/dataset-augmentation-for-pose-and-lighting
Repo
Framework

The Application of Preconditioned Alternating Direction Method of Multipliers in Depth from Focal Stack


Title	The Application of Preconditioned Alternating Direction Method of Multipliers in Depth from Focal Stack
Authors	Hossein Javidnia, Peter Corcoran
Abstract	Post capture refocusing effect in smartphone cameras is achievable by using focal stacks. However, the accuracy of this effect is totally dependent on the combination of the depth layers in the stack. The accuracy of the extended depth of field effect in this application can be improved significantly by computing an accurate depth map which has been an open issue for decades. To tackle this issue, in this paper, a framework is proposed based on Preconditioned Alternating Direction Method of Multipliers (PADMM) for depth from the focal stack and synthetic defocus application. In addition to its ability to provide high structural accuracy and occlusion handling, the optimization function of the proposed method can, in fact, converge faster and better than state of the art methods. The evaluation has been done on 21 sets of focal stacks and the optimization function has been compared against 5 other methods. Preliminary results indicate that the proposed method has a better performance in terms of structural accuracy and optimization in comparison to the current state of the art methods.
Tasks
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07721v1
PDF	http://arxiv.org/pdf/1711.07721v1.pdf
PWC	https://paperswithcode.com/paper/the-application-of-preconditioned-alternating
Repo
Framework

Data-adaptive Active Sampling for Efficient Graph-Cognizant Classification


Title	Data-adaptive Active Sampling for Efficient Graph-Cognizant Classification
Authors	Dimitris Berberidis, Georgios B. Giannakis
Abstract	The present work deals with active sampling of graph nodes representing training data for binary classification. The graph may be given or constructed using similarity measures among nodal features. Leveraging the graph for classification builds on the premise that labels across neighboring nodes are correlated according to a categorical Markov random field (MRF). This model is further relaxed to a Gaussian (G)MRF with labels taking continuous values - an approximation that not only mitigates the combinatorial complexity of the categorical model, but also offers optimal unbiased soft predictors of the unlabeled nodes. The proposed sampling strategy is based on querying the node whose label disclosure is expected to inflict the largest change on the GMRF, and in this sense it is the most informative on average. Such a strategy subsumes several measures of expected model change, including uncertainty sampling, variance minimization, and sampling based on the $\Sigma-$optimality criterion. A simple yet effective heuristic is also introduced for increasing the exploration capabilities of the sampler, and reducing bias of the resultant classifier, by taking into account the confidence on the model label predictions. The novel sampling strategies are based on quantities that are readily available without the need for model retraining, rendering them computationally efficient and scalable to large graphs. Numerical tests using synthetic and real data demonstrate that the proposed methods achieve accuracy that is comparable or superior to the state-of-the-art even at reduced runtime.
Tasks
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07220v3
PDF	http://arxiv.org/pdf/1705.07220v3.pdf
PWC	https://paperswithcode.com/paper/data-adaptive-active-sampling-for-efficient
Repo
Framework

Detection and classification of masses in mammographic images in a multi-kernel approach


Title	Detection and classification of masses in mammographic images in a multi-kernel approach
Authors	Sidney Marlon Lopes de Lima, Abel Guilhermino da Silva Filho, Wellington Pinheiro dos Santos
Abstract	According to the World Health Organization, breast cancer is the main cause of cancer death among adult women in the world. Although breast cancer occurs indiscriminately in countries with several degrees of social and economic development, among developing and underdevelopment countries mortality rates are still high, due to low availability of early detection technologies. From the clinical point of view, mammography is still the most effective diagnostic technology, given the wide diffusion of the use and interpretation of these images. Herein this work we propose a method to detect and classify mammographic lesions using the regions of interest of images. Our proposal consists in decomposing each image using multi-resolution wavelets. Zernike moments are extracted from each wavelet component. Using this approach we can combine both texture and shape features, which can be applied both to the detection and classification of mammary lesions. We used 355 images of fatty breast tissue of IRMA database, with 233 normal instances (no lesion), 72 benign, and 83 malignant cases. Classification was performed by using SVM and ELM networks with modified kernels, in order to optimize accuracy rates, reaching 94.11%. Considering both accuracy rates and training times, we defined the ration between average percentage accuracy and average training time in a reverse order. Our proposal was 50 times higher than the ratio obtained using the best method of the state-of-the-art. As our proposed model can combine high accuracy rate with low learning time, whenever a new data is received, our work will be able to save a lot of time, hours, in learning process in relation to the best method of the state-of-the-art.
Tasks
Published	2017-12-20
URL	http://arxiv.org/abs/1712.07116v1
PDF	http://arxiv.org/pdf/1712.07116v1.pdf
PWC	https://paperswithcode.com/paper/detection-and-classification-of-masses-in
Repo
Framework

An Adaptive Framework to Tune the Coordinate Systems in Evolutionary Algorithms


Title	An Adaptive Framework to Tune the Coordinate Systems in Evolutionary Algorithms
Authors	Zhi-Zhong Liu, Yong Wang, Shengxiang Yang, Ke Tang
Abstract	In the evolutionary computation research community, the performance of most evolutionary algorithms (EAs) depends strongly on their implemented coordinate system. However, the commonly used coordinate system is fixed and not well suited for different function landscapes, EAs thus might not search efficiently. To overcome this shortcoming, in this paper we propose a framework, named ACoS, to adaptively tune the coordinate systems in EAs. In ACoS, an Eigen coordinate system is established by making use of the cumulative population distribution information, which can be obtained based on a covariance matrix adaptation strategy and an additional archiving mechanism. Since the population distribution information can reflect the features of the function landscape to some extent, EAs in the Eigen coordinate system have the capability to identify the modality of the function landscape. In addition, the Eigen coordinate system is coupled with the original coordinate system, and they are selected according to a probability vector. The probability vector aims to determine the selection ratio of each coordinate system for each individual, and is adaptively updated based on the collected information from the offspring. ACoS has been applied to two of the most popular EA paradigms, i.e., particle swarm optimization (PSO) and differential evolution (DE), for solving 30 test functions with 30 and 50 dimensions at the 2014 IEEE Congress on Evolutionary Computation. The experimental studies demonstrate its effectiveness.
Tasks
Published	2017-03-18
URL	http://arxiv.org/abs/1703.06263v1
PDF	http://arxiv.org/pdf/1703.06263v1.pdf
PWC	https://paperswithcode.com/paper/an-adaptive-framework-to-tune-the-coordinate
Repo
Framework

What Can Help Pedestrian Detection?


Title	What Can Help Pedestrian Detection?
Authors	Jiayuan Mao, Tete Xiao, Yuning Jiang, Zhimin Cao
Abstract	Aggregating extra features has been considered as an effective approach to boost traditional pedestrian detection methods. However, there is still a lack of studies on whether and how CNN-based pedestrian detectors can benefit from these extra features. The first contribution of this paper is exploring this issue by aggregating extra features into CNN-based pedestrian detection framework. Through extensive experiments, we evaluate the effects of different kinds of extra features quantitatively. Moreover, we propose a novel network architecture, namely HyperLearner, to jointly learn pedestrian detection as well as the given extra feature. By multi-task training, HyperLearner is able to utilize the information of given features and improve detection performance without extra inputs in inference. The experimental results on multiple pedestrian benchmarks validate the effectiveness of the proposed HyperLearner.
Tasks	Pedestrian Detection
Published	2017-05-08
URL	http://arxiv.org/abs/1705.02757v1
PDF	http://arxiv.org/pdf/1705.02757v1.pdf
PWC	https://paperswithcode.com/paper/what-can-help-pedestrian-detection
Repo
Framework

Learning the Sparse and Low Rank PARAFAC Decomposition via the Elastic Net


Title	Learning the Sparse and Low Rank PARAFAC Decomposition via the Elastic Net
Authors	Songting Shi, Xiang Li, Arkadiusz Sitek, Quanzheng Li
Abstract	In this article, we derive a Bayesian model to learning the sparse and low rank PARAFAC decomposition for the observed tensor with missing values via the elastic net, with property to find the true rank and sparse factor matrix which is robust to the noise. We formulate efficient block coordinate descent algorithm and admax stochastic block coordinate descent algorithm to solve it, which can be used to solve the large scale problem. To choose the appropriate rank and sparsity in PARAFAC decomposition, we will give a solution path by gradually increasing the regularization to increase the sparsity and decrease the rank. When we find the sparse structure of the factor matrix, we can fixed the sparse structure, using a small to regularization to decreasing the recovery error, and one can choose the proper decomposition from the solution path with sufficient sparse factor matrix with low recovery error. We test the power of our algorithm on the simulation data and real data, which show it is powerful.
Tasks
Published	2017-05-29
URL	http://arxiv.org/abs/1705.10015v1
PDF	http://arxiv.org/pdf/1705.10015v1.pdf
PWC	https://paperswithcode.com/paper/learning-the-sparse-and-low-rank-parafac
Repo
Framework

Reparameterizing the Birkhoff Polytope for Variational Permutation Inference


Title	Reparameterizing the Birkhoff Polytope for Variational Permutation Inference
Authors	Scott W. Linderman, Gonzalo E. Mena, Hal Cooper, Liam Paninski, John P. Cunningham
Abstract	Many matching, tracking, sorting, and ranking problems require probabilistic reasoning about possible permutations, a set that grows factorially with dimension. Combinatorial optimization algorithms may enable efficient point estimation, but fully Bayesian inference poses a severe challenge in this high-dimensional, discrete space. To surmount this challenge, we start with the usual step of relaxing a discrete set (here, of permutation matrices) to its convex hull, which here is the Birkhoff polytope: the set of all doubly-stochastic matrices. We then introduce two novel transformations: first, an invertible and differentiable stick-breaking procedure that maps unconstrained space to the Birkhoff polytope; second, a map that rounds points toward the vertices of the polytope. Both transformations include a temperature parameter that, in the limit, concentrates the densities on permutation matrices. We then exploit these transformations and reparameterization gradients to introduce variational inference over permutation matrices, and we demonstrate its utility in a series of experiments.
Tasks	Bayesian Inference, Combinatorial Optimization
Published	2017-10-26
URL	http://arxiv.org/abs/1710.09508v1
PDF	http://arxiv.org/pdf/1710.09508v1.pdf
PWC	https://paperswithcode.com/paper/reparameterizing-the-birkhoff-polytope-for
Repo
Framework

Tensorial Recurrent Neural Networks for Longitudinal Data Analysis


Title	Tensorial Recurrent Neural Networks for Longitudinal Data Analysis
Authors	Mingyuan Bai, Boyan Zhang, Junbin Gao
Abstract	Traditional Recurrent Neural Networks assume vectorized data as inputs. However many data from modern science and technology come in certain structures such as tensorial time series data. To apply the recurrent neural networks for this type of data, a vectorisation process is necessary, while such a vectorisation leads to the loss of the precise information of the spatial or longitudinal dimensions. In addition, such a vectorized data is not an optimum solution for learning the representation of the longitudinal data. In this paper, we propose a new variant of tensorial neural networks which directly take tensorial time series data as inputs. We call this new variant as Tensorial Recurrent Neural Network (TRNN). The proposed TRNN is based on tensor Tucker decomposition.
Tasks	Time Series
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00185v1
PDF	http://arxiv.org/pdf/1708.00185v1.pdf
PWC	https://paperswithcode.com/paper/tensorial-recurrent-neural-networks-for
Repo
Framework