July 27, 2019

3050 words 15 mins read

Paper Group ANR 510

Continuous Implicit Authentication for Mobile Devices based on Adaptive Neuro-Fuzzy Inference System. CISRDCNN: Super-resolution of compressed images using deep convolutional neural networks. Machine Learning for Drug Overdose Surveillance. Implicit Regularization in Matrix Factorization. Two Stream LSTM: A Deep Fusion Framework for Human Action Re …

Continuous Implicit Authentication for Mobile Devices based on Adaptive Neuro-Fuzzy Inference System


Title	Continuous Implicit Authentication for Mobile Devices based on Adaptive Neuro-Fuzzy Inference System
Authors	Feng Yao, Suleiman Y. Yerima, BooJoong Kang, Sakir Sezer
Abstract	As mobile devices have become indispensable in modern life, mobile security is becoming much more important. Traditional password or PIN-like point-of-entry security measures score low on usability and are vulnerable to brute force and other types of attacks. In order to improve mobile security, an adaptive neuro-fuzzy inference system(ANFIS)-based implicit authentication system is proposed in this paper to provide authentication in a continuous and transparent manner.To illustrate the applicability and capability of ANFIS in our implicit authentication system, experiments were conducted on behavioural data collected for up to 12 weeks from different Android users. The ability of the ANFIS-based system to detect an adversary is also tested with scenarios involving an attacker with varying levels of knowledge. The results demonstrate that ANFIS is a feasible and efficient approach for implicit authentication with an average of 95% user recognition rate. Moreover, the use of ANFIS-based system for implicit authentication significantly reduces manual tuning and configuration tasks due to its selflearning capability.
Tasks	Mobile Security
Published	2017-05-18
URL	http://arxiv.org/abs/1705.06715v1
PDF	http://arxiv.org/pdf/1705.06715v1.pdf
PWC	https://paperswithcode.com/paper/continuous-implicit-authentication-for-mobile
Repo
Framework

CISRDCNN: Super-resolution of compressed images using deep convolutional neural networks


Title	CISRDCNN: Super-resolution of compressed images using deep convolutional neural networks
Authors	Honggang Chen, Xiaohai He, Chao Ren, Linbo Qing, Qizhi Teng
Abstract	In recent years, much research has been conducted on image super-resolution (SR). To the best of our knowledge, however, few SR methods were concerned with compressed images. The SR of compressed images is a challenging task due to the complicated compression artifacts, while many images suffer from them in practice. The intuitive solution for this difficult task is to decouple it into two sequential but independent subproblems, i.e., compression artifacts reduction (CAR) and SR. Nevertheless, some useful details may be removed in CAR stage, which is contrary to the goal of SR and makes the SR stage more challenging. In this paper, an end-to-end trainable deep convolutional neural network is designed to perform SR on compressed images (CISRDCNN), which reduces compression artifacts and improves image resolution jointly. Experiments on compressed images produced by JPEG (we take the JPEG as an example in this paper) demonstrate that the proposed CISRDCNN yields state-of-the-art SR performance on commonly used test images and imagesets. The results of CISRDCNN on real low quality web images are also very impressive, with obvious quality enhancement. Further, we explore the application of the proposed SR method in low bit-rate image coding, leading to better rate-distortion performance than JPEG.
Tasks	Image Super-Resolution, Super-Resolution
Published	2017-09-19
URL	http://arxiv.org/abs/1709.06229v1
PDF	http://arxiv.org/pdf/1709.06229v1.pdf
PWC	https://paperswithcode.com/paper/cisrdcnn-super-resolution-of-compressed
Repo
Framework

Machine Learning for Drug Overdose Surveillance


Title	Machine Learning for Drug Overdose Surveillance
Authors	Daniel B. Neill, William Herlands
Abstract	We describe two recently proposed machine learning approaches for discovering emerging trends in fatal accidental drug overdoses. The Gaussian Process Subset Scan enables early detection of emerging patterns in spatio-temporal data, accounting for both the non-iid nature of the data and the fact that detecting subtle patterns requires integration of information across multiple spatial areas and multiple time steps. We apply this approach to 17 years of county-aggregated data for monthly opioid overdose deaths in the New York City metropolitan area, showing clear advantages in the utility of discovered patterns as compared to typical anomaly detection approaches. To detect and characterize emerging overdose patterns that differentially affect a subpopulation of the data, including geographic, demographic, and behavioral patterns (e.g., which combinations of drugs are involved), we apply the Multidimensional Tensor Scan to 8 years of case-level overdose data from Allegheny County, PA. We discover previously unidentified overdose patterns which reveal unusual demographic clusters, show impacts of drug legislation, and demonstrate potential for early detection and targeted intervention. These approaches to early detection of overdose patterns can inform prevention and response efforts, as well as understanding the effects of policy changes.
Tasks	Anomaly Detection
Published	2017-10-06
URL	http://arxiv.org/abs/1710.02458v1
PDF	http://arxiv.org/pdf/1710.02458v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-for-drug-overdose
Repo
Framework

Implicit Regularization in Matrix Factorization


Title	Implicit Regularization in Matrix Factorization
Authors	Suriya Gunasekar, Blake Woodworth, Srinadh Bhojanapalli, Behnam Neyshabur, Nathan Srebro
Abstract	We study implicit regularization when optimizing an underdetermined quadratic objective over a matrix $X$ with gradient descent on a factorization of $X$. We conjecture and provide empirical and theoretical evidence that with small enough step sizes and initialization close enough to the origin, gradient descent on a full dimensional factorization converges to the minimum nuclear norm solution.
Tasks
Published	2017-05-25
URL	http://arxiv.org/abs/1705.09280v1
PDF	http://arxiv.org/pdf/1705.09280v1.pdf
PWC	https://paperswithcode.com/paper/implicit-regularization-in-matrix
Repo
Framework

Two Stream LSTM: A Deep Fusion Framework for Human Action Recognition


Title	Two Stream LSTM: A Deep Fusion Framework for Human Action Recognition
Authors	Harshala Gammulle, Simon Denman, Sridha Sridharan, Clinton Fookes
Abstract	In this paper we address the problem of human action recognition from video sequences. Inspired by the exemplary results obtained via automatic feature learning and deep learning approaches in computer vision, we focus our attention towards learning salient spatial features via a convolutional neural network (CNN) and then map their temporal relationship with the aid of Long-Short-Term-Memory (LSTM) networks. Our contribution in this paper is a deep fusion framework that more effectively exploits spatial features from CNNs with temporal features from LSTM models. We also extensively evaluate their strengths and weaknesses. We find that by combining both the sets of features, the fully connected features effectively act as an attention mechanism to direct the LSTM to interesting parts of the convolutional feature sequence. The significance of our fusion method is its simplicity and effectiveness compared to other state-of-the-art methods. The evaluation results demonstrate that this hierarchical multi stream fusion method has higher performance compared to single stream mapping methods allowing it to achieve high accuracy outperforming current state-of-the-art methods in three widely used databases: UCF11, UCFSports, jHMDB.
Tasks	Temporal Action Localization
Published	2017-04-04
URL	http://arxiv.org/abs/1704.01194v1
PDF	http://arxiv.org/pdf/1704.01194v1.pdf
PWC	https://paperswithcode.com/paper/two-stream-lstm-a-deep-fusion-framework-for
Repo
Framework

Sampling Without Time: Recovering Echoes of Light via Temporal Phase Retrieval


Title	Sampling Without Time: Recovering Echoes of Light via Temporal Phase Retrieval
Authors	Ayush Bhandari, Aurelien Bourquard, Ramesh Raskar
Abstract	This paper considers the problem of sampling and reconstruction of a continuous-time sparse signal without assuming the knowledge of the sampling instants or the sampling rate. This topic has its roots in the problem of recovering multiple echoes of light from its low-pass filtered and auto-correlated, time-domain measurements. Our work is closely related to the topic of sparse phase retrieval and in this context, we discuss the advantage of phase-free measurements. While this problem is ill-posed, cues based on physical constraints allow for its appropriate regularization. We validate our theory with experiments based on customized, optical time-of-flight imaging sensors. What singles out our approach is that our sensing method allows for temporal phase retrieval as opposed to the usual case of spatial phase retrieval. Preliminary experiments and results demonstrate a compelling capability of our phase-retrieval based imaging device.
Tasks
Published	2017-01-27
URL	http://arxiv.org/abs/1701.08222v1
PDF	http://arxiv.org/pdf/1701.08222v1.pdf
PWC	https://paperswithcode.com/paper/sampling-without-time-recovering-echoes-of
Repo
Framework

Prior and Likelihood Choices for Bayesian Matrix Factorisation on Small Datasets


Title	Prior and Likelihood Choices for Bayesian Matrix Factorisation on Small Datasets
Authors	Thomas Brouwer, Pietro Lio’
Abstract	In this paper, we study the effects of different prior and likelihood choices for Bayesian matrix factorisation, focusing on small datasets. These choices can greatly influence the predictive performance of the methods. We identify four groups of approaches: Gaussian-likelihood with real-valued priors, nonnegative priors, semi-nonnegative models, and finally Poisson-likelihood approaches. For each group we review several models from the literature, considering sixteen in total, and discuss the relations between different priors and matrix norms. We extensively compare these methods on eight real-world datasets across three application areas, giving both inter- and intra-group comparisons. We measure convergence runtime speed, cross-validation performance, sparse and noisy prediction performance, and model selection robustness. We offer several insights into the trade-offs between prior and likelihood choices for Bayesian matrix factorisation on small datasets - such as that Poisson models give poor predictions, and that nonnegative models are more constrained than real-valued ones.
Tasks	Model Selection
Published	2017-12-01
URL	http://arxiv.org/abs/1712.00288v1
PDF	http://arxiv.org/pdf/1712.00288v1.pdf
PWC	https://paperswithcode.com/paper/prior-and-likelihood-choices-for-bayesian
Repo
Framework

Relaxed Wasserstein with Applications to GANs


Title	Relaxed Wasserstein with Applications to GANs
Authors	Xin Guo, Johnny Hong, Tianyi Lin, Nan Yang
Abstract	Comparing probability distributions is an integral part of many modern data-driven applications, such as generative adversarial networks (GANs) and distributionally robust optimization (DRO). We propose a novel class of statistical divergences called \textit{Relaxed Wasserstein} (RW) divergence, which generalizes Wasserstein divergence and is parametrized by the class of strictly convex and differentiable functions. We establish for RW divergence several probabilistic properties, many of which are crucial for the success of Wasserstein divergence. In addition, we derive theoretical results showing that the underlying convex function in RW plays an important role in variance stabilization, shedding light on the choice of appropriate convex function. We develop a version of GANs based on RW divergence and demonstrate via empirical experiments that RW-based GANs (RWGANs) lead to superior performance in image generation problems compared to existing approaches. In particular, we find that in our experiments RWGANs are fastest in generating meaningful images compared to other GANs. We also illustrate the use of RW divergence in constructing ambiguity sets for DRO problems, and the robust portfolio problem under mean-variance framework.
Tasks	Image Generation
Published	2017-05-19
URL	https://arxiv.org/abs/1705.07164v5
PDF	https://arxiv.org/pdf/1705.07164v5.pdf
PWC	https://paperswithcode.com/paper/relaxed-wasserstein-with-applications-to-gans
Repo
Framework

Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding


Title	Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding
Authors	Bing Liu, Ian Lane
Abstract	The goal of this paper is to learn cross-domain representations for slot filling task in spoken language understanding (SLU). Most of the recently published SLU models are domain-specific ones that work on individual task domains. Annotating data for each individual task domain is both financially costly and non-scalable. In this work, we propose an adversarial training method in learning common features and representations that can be shared across multiple domains. Model that produces such shared representations can be combined with models trained on individual domain SLU data to reduce the amount of training samples required for developing a new domain. In our experiments using data sets from multiple domains, we show that adversarial training helps in learning better domain-general SLU models, leading to improved slot filling F1 scores. We further show that applying adversarial learning on domain-general model also helps in achieving higher slot filling performance when the model is jointly optimized with domain-specific models.
Tasks	Slot Filling, Spoken Language Understanding
Published	2017-11-30
URL	http://arxiv.org/abs/1711.11310v1
PDF	http://arxiv.org/pdf/1711.11310v1.pdf
PWC	https://paperswithcode.com/paper/multi-domain-adversarial-learning-for-slot
Repo
Framework

Semantic Interpolation in Implicit Models


Title	Semantic Interpolation in Implicit Models
Authors	Yannic Kilcher, Aurelien Lucchi, Thomas Hofmann
Abstract	In implicit models, one often interpolates between sampled points in latent space. As we show in this paper, care needs to be taken to match-up the distributional assumptions on code vectors with the geometry of the interpolating paths. Otherwise, typical assumptions about the quality and semantics of in-between points may not be justified. Based on our analysis we propose to modify the prior code distribution to put significantly more probability mass closer to the origin. As a result, linear interpolation paths are not only shortest paths, but they are also guaranteed to pass through high-density regions, irrespective of the dimensionality of the latent space. Experiments on standard benchmark image datasets demonstrate clear visual improvements in the quality of the generated samples and exhibit more meaningful interpolation paths.
Tasks
Published	2017-10-31
URL	http://arxiv.org/abs/1710.11381v3
PDF	http://arxiv.org/pdf/1710.11381v3.pdf
PWC	https://paperswithcode.com/paper/semantic-interpolation-in-implicit-models
Repo
Framework

Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reduction


Title	Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reduction
Authors	Bin Liang, Hongcheng Li, Miaoqiang Su, Xirong Li, Wenchang Shi, Xiaofeng Wang
Abstract	Recently, many studies have demonstrated deep neural network (DNN) classifiers can be fooled by the adversarial example, which is crafted via introducing some perturbations into an original sample. Accordingly, some powerful defense techniques were proposed. However, existing defense techniques often require modifying the target model or depend on the prior knowledge of attacks. In this paper, we propose a straightforward method for detecting adversarial image examples, which can be directly deployed into unmodified off-the-shelf DNN models. We consider the perturbation to images as a kind of noise and introduce two classic image processing techniques, scalar quantization and smoothing spatial filter, to reduce its effect. The image entropy is employed as a metric to implement an adaptive noise reduction for different kinds of images. Consequently, the adversarial example can be effectively detected by comparing the classification results of a given sample and its denoised version, without referring to any prior knowledge of attacks. More than 20,000 adversarial examples against some state-of-the-art DNN models are used to evaluate the proposed method, which are crafted with different attack techniques. The experiments show that our detection method can achieve a high overall F1 score of 96.39% and certainly raises the bar for defense-aware attacks.
Tasks	Quantization
Published	2017-05-23
URL	http://arxiv.org/abs/1705.08378v5
PDF	http://arxiv.org/pdf/1705.08378v5.pdf
PWC	https://paperswithcode.com/paper/detecting-adversarial-image-examples-in-deep
Repo
Framework

When is Network Lasso Accurate?


Title	When is Network Lasso Accurate?
Authors	Alexander Jung, Nguyen Tran Quang, Alexandru Mara
Abstract	The “least absolute shrinkage and selection operator” (Lasso) method has been adapted recently for networkstructured datasets. In particular, this network Lasso method allows to learn graph signals from a small number of noisy signal samples by using the total variation of a graph signal for regularization. While efficient and scalable implementations of the network Lasso are available, only little is known about the conditions on the underlying network structure which ensure network Lasso to be accurate. By leveraging concepts of compressed sensing, we address this gap and derive precise conditions on the underlying network topology and sampling set which guarantee the network Lasso for a particular loss function to deliver an accurate estimate of the entire underlying graph signal. We also quantify the error incurred by network Lasso in terms of two constants which reflect the connectivity of the sampled nodes.
Tasks
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02107v3
PDF	http://arxiv.org/pdf/1704.02107v3.pdf
PWC	https://paperswithcode.com/paper/when-is-network-lasso-accurate
Repo
Framework

DynASP2.5: Dynamic Programming on Tree Decompositions in Action


Title	DynASP2.5: Dynamic Programming on Tree Decompositions in Action
Authors	Johannes K. Fichte, Markus Hecher, Michael Morak, Stefan Woltran
Abstract	A vibrant theoretical research area are efficient exact parameterized algorithms. Very recent solving competitions such as the PACE challenge show that there is also increasing practical interest in the parameterized algorithms community. An important research question is whether dedicated parameterized exact algorithms exhibit certain practical relevance and one can even beat well-established problem solvers. We consider the logic-based declarative modeling language and problem solving framework Answer Set Programming (ASP). State-of-the-art ASP solvers rely considerably on Sat-based algorithms. An ASP solver (DynASP2), which is based on a classical dynamic programming on tree decompositions, has been published very recently. Unfortunately, DynASP2 can outperform modern ASP solvers on programs of small treewidth only if the question of interest is to count the number of solutions. In this paper, we describe underlying concepts of our new implementation (DynASP2.5) that shows competitive behavior to state-of-the-art ASP solvers even for finding just one solution when solving problems as the Steiner tree problem that have been modeled in ASP on graphs with low treewidth. Our implementation is based on a novel approach that we call multi-pass dynamic programming (M-DPSINC).
Tasks
Published	2017-06-28
URL	http://arxiv.org/abs/1706.09370v1
PDF	http://arxiv.org/pdf/1706.09370v1.pdf
PWC	https://paperswithcode.com/paper/dynasp25-dynamic-programming-on-tree
Repo
Framework

Lensless-camera based machine learning for image classification


Title	Lensless-camera based machine learning for image classification
Authors	Ganghun Kim, Stefan Kapetanovic, Rachael Palmer, Rajesh Menon
Abstract	Machine learning (ML) has been widely applied to image classification. Here, we extend this application to data generated by a camera comprised of only a standard CMOS image sensor with no lens. We first created a database of lensless images of handwritten digits. Then, we trained a ML algorithm on this dataset. Finally, we demonstrated that the trained ML algorithm is able to classify the digits with accuracy as high as 99% for 2 digits. Our approach clearly demonstrates the potential for non-human cameras in machine-based decision-making scenarios.
Tasks	Decision Making, Image Classification
Published	2017-09-03
URL	http://arxiv.org/abs/1709.00408v1
PDF	http://arxiv.org/pdf/1709.00408v1.pdf
PWC	https://paperswithcode.com/paper/lensless-camera-based-machine-learning-for
Repo
Framework

Texture Classification of MR Images of the Brain in ALS using CoHOG


Title	Texture Classification of MR Images of the Brain in ALS using CoHOG
Authors	G M Mashrur E Elahi, Sanjay Kalra, Yee-Hong Yang
Abstract	Texture analysis is a well-known research topic in computer vision and image processing and has many applications. Gradient-based texture methods have become popular in classification problems. For the first time we extend a well-known gradient-based method, Co-occurrence Histograms of Oriented Gradients (CoHOG) to extract texture features from 2D Magnetic Resonance Images (MRI). Unlike the original CoHOG method, we use the whole image instead of sub-regions for feature calculation. Also, we use a larger neighborhood size. Gradient orientations of the image pixels are calculated using Sobel, Gaussian Derivative (GD) and Local Frequency Descriptor Gradient (LFDG) operators. The extracted feature vector size is very large and classification using a large number of similar features does not provide the best results. In our proposed method, for the first time to our best knowledge, only a minimum number of significant features are selected using area under the receiver operator characteristic (ROC) curve (AUC) thresholds with <= 0.01. In this paper, we apply the proposed method to classify Amyotrophic Lateral Sclerosis (ALS) patients from the controls. It is observed that selected texture features from downsampled images are significantly different between patients and controls. These features are used in a linear support vector machine (SVM) classifier to determine the classification accuracy. Optimal sensitivity and specificity are also calculated. Three different cohort datasets are used in the experiments. The performance of the proposed method using three gradient operators and two different neighborhood sizes is analyzed. Region based analysis is performed to demonstrate that significant changes between patients and controls are limited to the motor cortex.
Tasks	Texture Classification
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02589v2
PDF	http://arxiv.org/pdf/1703.02589v2.pdf
PWC	https://paperswithcode.com/paper/texture-classification-of-mr-images-of-the
Repo
Framework