May 7, 2019

3242 words 16 mins read

Paper Group ANR 52

CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases. Further properties of the forward-backward envelope with applications to difference-of-convex programming. Efficient KLMS and KRLS Algorithms: A Random Fourier Feature Perspective. Benign-Malignant Lung Nodule Classification with Geometric and Appearance Histogram …

CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases


Title	CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases
Authors	Zihang Dai, Lei Li, Wei Xu
Abstract	How can we enable computers to automatically answer questions like “Who created the character Harry Potter”? Carefully built knowledge bases provide rich sources of facts. However, it remains a challenge to answer factoid questions raised in natural language due to numerous expressions of one question. In particular, we focus on the most common questions — ones that can be answered with a single fact in the knowledge base. We propose CFO, a Conditional Focused neural-network-based approach to answering factoid questions with knowledge bases. Our approach first zooms in a question to find more probable candidate subject mentions, and infers the final answers with a unified conditional probabilistic framework. Powered by deep recurrent neural networks and neural embeddings, our proposed CFO achieves an accuracy of 75.7% on a dataset of 108k questions - the largest public one to date. It outperforms the current state of the art by an absolute margin of 11.8%.
Tasks	Question Answering
Published	2016-06-07
URL	http://arxiv.org/abs/1606.01994v2
PDF	http://arxiv.org/pdf/1606.01994v2.pdf
PWC	https://paperswithcode.com/paper/cfo-conditional-focused-neural-question
Repo
Framework

Further properties of the forward-backward envelope with applications to difference-of-convex programming


Title	Further properties of the forward-backward envelope with applications to difference-of-convex programming
Authors	Tianxiang Liu, Ting Kei Pong
Abstract	In this paper, we further study the forward-backward envelope first introduced in [28] and [30] for problems whose objective is the sum of a proper closed convex function and a twice continuously differentiable possibly nonconvex function with Lipschitz continuous gradient. We derive sufficient conditions on the original problem for the corresponding forward-backward envelope to be a level-bounded and Kurdyka-{\L}ojasiewicz function with an exponent of $\frac12$; these results are important for the efficient minimization of the forward-backward envelope by classical optimization algorithms. In addition, we demonstrate how to minimize some difference-of-convex regularized least squares problems by minimizing a suitably constructed forward-backward envelope. Our preliminary numerical results on randomly generated instances of large-scale $\ell_{1-2}$ regularized least squares problems [37] illustrate that an implementation of this approach with a limited-memory BFGS scheme usually outperforms standard first-order methods such as the nonmonotone proximal gradient method in [35].
Tasks
Published	2016-05-01
URL	http://arxiv.org/abs/1605.00201v4
PDF	http://arxiv.org/pdf/1605.00201v4.pdf
PWC	https://paperswithcode.com/paper/further-properties-of-the-forward-backward
Repo
Framework

Efficient KLMS and KRLS Algorithms: A Random Fourier Feature Perspective


Title	Efficient KLMS and KRLS Algorithms: A Random Fourier Feature Perspective
Authors	Pantelis Bouboulis, Spyridon Pougkakiotis, Sergios Theodoridis
Abstract	We present a new framework for online Least Squares algorithms for nonlinear modeling in RKH spaces (RKHS). Instead of implicitly mapping the data to a RKHS (e.g., kernel trick), we map the data to a finite dimensional Euclidean space, using random features of the kernel’s Fourier transform. The advantage is that, the inner product of the mapped data approximates the kernel function. The resulting “linear” algorithm does not require any form of sparsification, since, in contrast to all existing algorithms, the solution’s size remains fixed and does not increase with the iteration steps. As a result, the obtained algorithms are computationally significantly more efficient compared to previously derived variants, while, at the same time, they converge at similar speeds and to similar error floors.
Tasks
Published	2016-06-12
URL	http://arxiv.org/abs/1606.03685v1
PDF	http://arxiv.org/pdf/1606.03685v1.pdf
PWC	https://paperswithcode.com/paper/efficient-klms-and-krls-algorithms-a-random
Repo
Framework

Benign-Malignant Lung Nodule Classification with Geometric and Appearance Histogram Features


Title	Benign-Malignant Lung Nodule Classification with Geometric and Appearance Histogram Features
Authors	Tizita Nesibu Shewaye, Alhayat Ali Mekonnen
Abstract	Lung cancer accounts for the highest number of cancer deaths globally. Early diagnosis of lung nodules is very important to reduce the mortality rate of patients by improving the diagnosis and treatment of lung cancer. This work proposes an automated system to classify lung nodules as malignant and benign in CT images. It presents extensive experimental results using a combination of geometric and histogram lung nodule image features and different linear and non-linear discriminant classifiers. The proposed approach is experimentally validated on the LIDC-IDRI public lung cancer screening thoracic computed tomography (CT) dataset containing nodule level diagnostic data. The obtained results are very encouraging correctly classifying 82% of malignant and 93% of benign nodules on unseen test data at best.
Tasks	Computed Tomography (CT), Lung Nodule Classification
Published	2016-05-26
URL	http://arxiv.org/abs/1605.08350v1
PDF	http://arxiv.org/pdf/1605.08350v1.pdf
PWC	https://paperswithcode.com/paper/benign-malignant-lung-nodule-classification
Repo
Framework

Fuzzy c-Shape: A new algorithm for clustering finite time series waveforms


Title	Fuzzy c-Shape: A new algorithm for clustering finite time series waveforms
Authors	Fateme Fahiman, Jame C. Bezdek, Sarah M. Erfani, Christopher Leckie, Marimuthu Palaniswami
Abstract	The existence of large volumes of time series data in many applications has motivated data miners to investigate specialized methods for mining time series data. Clustering is a popular data mining method due to its powerful exploratory nature and its usefulness as a preprocessing step for other data mining techniques. This article develops two novel clustering algorithms for time series data that are extensions of a crisp c-shapes algorithm. The two new algorithms are heuristic derivatives of fuzzy c-means (FCM). Fuzzy c-Shapes plus (FCS+) replaces the inner product norm in the FCM model with a shape-based distance function. Fuzzy c-Shapes double plus (FCS++) uses the shape-based distance, and also replaces the FCM cluster centers with shape-extracted prototypes. Numerical experiments on 48 real time series data sets show that the two new algorithms outperform state-of-the-art shape-based clustering algorithms in terms of accuracy and efficiency. Four external cluster validity indices (the Rand index, Adjusted Rand Index, Variation of Information, and Normalized Mutual Information) are used to match candidate partitions generated by each of the studied algorithms. All four indices agree that for these finite waveform data sets, FCS++ gives a small improvement over FCS+, and in turn, FCS+ is better than the original crisp c-shapes method. Finally, we apply two tests of statistical significance to the three algorithms. The Wilcoxon and Friedman statistics both rank the three algorithms in exactly the same way as the four cluster validity indices.
Tasks	Time Series
Published	2016-08-03
URL	http://arxiv.org/abs/1608.01072v1
PDF	http://arxiv.org/pdf/1608.01072v1.pdf
PWC	https://paperswithcode.com/paper/fuzzy-c-shape-a-new-algorithm-for-clustering
Repo
Framework

Accurate Deep Representation Quantization with Gradient Snapping Layer for Similarity Search


Title	Accurate Deep Representation Quantization with Gradient Snapping Layer for Similarity Search
Authors	Shicong Liu, Hongtao Lu
Abstract	Recent advance of large scale similarity search involves using deeply learned representations to improve the search accuracy and use vector quantization methods to increase the search speed. However, how to learn deep representations that strongly preserve similarities between data pairs and can be accurately quantized via vector quantization remains a challenging task. Existing methods simply leverage quantization loss and similarity loss, which result in unexpectedly biased back-propagating gradients and affect the search performances. To this end, we propose a novel gradient snapping layer (GSL) to directly regularize the back-propagating gradient towards a neighboring codeword, the generated gradients are un-biased for reducing similarity loss and also propel the learned representations to be accurately quantized. Joint deep representation and vector quantization learning can be easily performed by alternatively optimize the quantization codebook and the deep neural network. The proposed framework is compatible with various existing vector quantization approaches. Experimental results demonstrate that the proposed framework is effective, flexible and outperforms the state-of-the-art large scale similarity search methods.
Tasks	Quantization
Published	2016-10-30
URL	http://arxiv.org/abs/1610.09645v1
PDF	http://arxiv.org/pdf/1610.09645v1.pdf
PWC	https://paperswithcode.com/paper/accurate-deep-representation-quantization
Repo
Framework

A three-dimensional approach to Visual Speech Recognition using Discrete Cosine Transforms


Title	A three-dimensional approach to Visual Speech Recognition using Discrete Cosine Transforms
Authors	Toni Heidenreich, Michael W. Spratling
Abstract	Visual speech recognition aims to identify the sequence of phonemes from continuous speech. Unlike the traditional approach of using 2D image feature extraction methods to derive features of each video frame separately, this paper proposes a new approach using a 3D (spatio-temporal) Discrete Cosine Transform to extract features of each feasible sub-sequence of an input video which are subsequently classified individually using Support Vector Machines and combined to find the most likely phoneme sequence using a tailor-made Hidden Markov Model. The algorithm is trained and tested on the VidTimit database to recognise sequences of phonemes as well as visemes (visual speech units). Furthermore, the system is extended with the training on phoneme or viseme pairs (biphones) to counteract the human speech ambiguity of co-articulation. The test set accuracy for the recognition of phoneme sequences is 20%, and the accuracy of viseme sequences is 39%. Both results improve the best values reported in other papers by approximately 2%. The contribution of the result is three-fold: Firstly, this paper is the first to show that 3D feature extraction methods can be applied to continuous sequence recognition tasks despite the unknown start positions and durations of each phoneme. Secondly, the result confirms that 3D feature extraction methods improve the accuracy compared to 2D features extraction methods. Thirdly, the paper is the first to specifically compare an otherwise identical method with and without using biphones, verifying that the usage of biphones has a positive impact on the result.
Tasks	Speech Recognition, Visual Speech Recognition
Published	2016-09-07
URL	http://arxiv.org/abs/1609.01932v1
PDF	http://arxiv.org/pdf/1609.01932v1.pdf
PWC	https://paperswithcode.com/paper/a-three-dimensional-approach-to-visual-speech
Repo
Framework

Improving SAT Solvers via Blocked Clause Decomposition


Title	Improving SAT Solvers via Blocked Clause Decomposition
Authors	Jingchao Chen
Abstract	The decision variable selection policy used by the most competitive CDCL (Conflict-Driven Clause Learning) SAT solvers is either VSIDS (Variable State Independent Decaying Sum) or its variants such as exponential version EVSIDS. The common characteristic of VSIDS and its variants is to make use of statistical information in the solving process, but ignore structure information of the problem. For this reason, this paper modifies the decision variable selection policy, and presents a SAT solving technique based on BCD (Blocked Clause Decomposition). Its basic idea is that a part of decision variables are selected by VSIDS heuristic, while another part of decision variables are selected by blocked sets that are obtained by BCD. Compared with the existing BCD-based technique, our technique is simple, and need not to reencode CNF formulas. SAT solvers for certified UNSAT track can apply also our BCD-based technique. Our experiments on application benchmarks demonstrate that the new variables selection policy based on BCD can increase the performance of SAT solvers such as abcdSAT. The solver with BCD solved an instance from the SAT Race 2015 that was not solved by any solver so far. This shows that in some cases, the heuristic based on structure information is more efficient than that based on statistical information.
Tasks
Published	2016-04-02
URL	http://arxiv.org/abs/1604.00536v1
PDF	http://arxiv.org/pdf/1604.00536v1.pdf
PWC	https://paperswithcode.com/paper/improving-sat-solvers-via-blocked-clause
Repo
Framework

Global-Local Face Upsampling Network


Title	Global-Local Face Upsampling Network
Authors	Oncel Tuzel, Yuichi Taguchi, John R. Hershey
Abstract	Face hallucination, which is the task of generating a high-resolution face image from a low-resolution input image, is a well-studied problem that is useful in widespread application areas. Face hallucination is particularly challenging when the input face resolution is very low (e.g., 10 x 12 pixels) and/or the image is captured in an uncontrolled setting with large pose and illumination variations. In this paper, we revisit the algorithm introduced in [1] and present a deep interpretation of this framework that achieves state-of-the-art under such challenging scenarios. In our deep network architecture the global and local constraints that define a face can be efficiently modeled and learned end-to-end using training data. Conceptually our network design can be partitioned into two sub-networks: the first one implements the holistic face reconstruction according to global constraints, and the second one enhances face-specific details and enforces local patch statistics. We optimize the deep network using a new loss function for super-resolution that combines reconstruction error with a learned face quality measure in adversarial setting, producing improved visual results. We conduct extensive experiments in both controlled and uncontrolled setups and show that our algorithm improves the state of the art both numerically and visually.
Tasks	Face Hallucination, Face Reconstruction, Super-Resolution
Published	2016-03-23
URL	http://arxiv.org/abs/1603.07235v2
PDF	http://arxiv.org/pdf/1603.07235v2.pdf
PWC	https://paperswithcode.com/paper/global-local-face-upsampling-network
Repo
Framework

Camera Elevation Estimation from a Single Mountain Landscape Photograph


Title	Camera Elevation Estimation from a Single Mountain Landscape Photograph
Authors	Martin Cadik, Jan Vasicek, Michal Hradis, Filip Radenovic, Ondrej Chum
Abstract	This work addresses the problem of camera elevation estimation from a single photograph in an outdoor environment. We introduce a new benchmark dataset of one-hundred thousand images with annotated camera elevation called Alps100K. We propose and experimentally evaluate two automatic data-driven approaches to camera elevation estimation: one based on convolutional neural networks, the other on local features. To compare the proposed methods to human performance, an experiment with 100 subjects is conducted. The experimental results show that both proposed approaches outperform humans and that the best result is achieved by their combination.
Tasks
Published	2016-07-12
URL	http://arxiv.org/abs/1607.03305v1
PDF	http://arxiv.org/pdf/1607.03305v1.pdf
PWC	https://paperswithcode.com/paper/camera-elevation-estimation-from-a-single
Repo
Framework

A Large-scale Distributed Video Parsing and Evaluation Platform


Title	A Large-scale Distributed Video Parsing and Evaluation Platform
Authors	Kai Yu, Yang Zhou, Da Li, Zhang Zhang, Kaiqi Huang
Abstract	Visual surveillance systems have become one of the largest data sources of Big Visual Data in real world. However, existing systems for video analysis still lack the ability to handle the problems of scalability, expansibility and error-prone, though great advances have been achieved in a number of visual recognition tasks and surveillance applications, e.g., pedestrian/vehicle detection, people/vehicle counting. Moreover, few algorithms explore the specific values/characteristics in large-scale surveillance videos. To address these problems in large-scale video analysis, we develop a scalable video parsing and evaluation platform through combining some advanced techniques for Big Data processing, including Spark Streaming, Kafka and Hadoop Distributed Filesystem (HDFS). Also, a Web User Interface is designed in the system, to collect users’ degrees of satisfaction on the recognition tasks so as to evaluate the performance of the whole system. Furthermore, the highly extensible platform running on the long-term surveillance videos makes it possible to develop more intelligent incremental algorithms to enhance the performance of various visual recognition tasks.
Tasks
Published	2016-11-29
URL	http://arxiv.org/abs/1611.09580v1
PDF	http://arxiv.org/pdf/1611.09580v1.pdf
PWC	https://paperswithcode.com/paper/a-large-scale-distributed-video-parsing-and
Repo
Framework

Contrastive Structured Anomaly Detection for Gaussian Graphical Models


Title	Contrastive Structured Anomaly Detection for Gaussian Graphical Models
Authors	Abhinav Maurya, Mark Cheung
Abstract	Gaussian graphical models (GGMs) are probabilistic tools of choice for analyzing conditional dependencies between variables in complex systems. Finding changepoints in the structural evolution of a GGM is therefore essential to detecting anomalies in the underlying system modeled by the GGM. In order to detect structural anomalies in a GGM, we consider the problem of estimating changes in the precision matrix of the corresponding Gaussian distribution. We take a two-step approach to solving this problem:- (i) estimating a background precision matrix using system observations from the past without any anomalies, and (ii) estimating a foreground precision matrix using a sliding temporal window during anomaly monitoring. Our primary contribution is in estimating the foreground precision using a novel contrastive inverse covariance estimation procedure. In order to accurately learn only the structural changes to the GGM, we maximize a penalized log-likelihood where the penalty is the $l_1$ norm of difference between the foreground precision being estimated and the already learned background precision. We modify the alternating direction method of multipliers (ADMM) algorithm for sparse inverse covariance estimation to perform contrastive estimation of the foreground precision matrix. Our results on simulated GGM data show significant improvement in precision and recall for detecting structural changes to the GGM, compared to a non-contrastive sliding window baseline.
Tasks	Anomaly Detection
Published	2016-05-02
URL	http://arxiv.org/abs/1605.00355v1
PDF	http://arxiv.org/pdf/1605.00355v1.pdf
PWC	https://paperswithcode.com/paper/contrastive-structured-anomaly-detection-for
Repo
Framework

Fractional Order Fuzzy Control of Hybrid Power System with Renewable Generation Using Chaotic PSO


Title	Fractional Order Fuzzy Control of Hybrid Power System with Renewable Generation Using Chaotic PSO
Authors	Indranil Pan, Saptarshi Das
Abstract	This paper investigates the operation of a hybrid power system through a novel fuzzy control scheme. The hybrid power system employs various autonomous generation systems like wind turbine, solar photovoltaic, diesel engine, fuel-cell, aqua electrolyzer etc. Other energy storage devices like the battery, flywheel and ultra-capacitor are also present in the network. A novel fractional order (FO) fuzzy control scheme is employed and its parameters are tuned with a particle swarm optimization (PSO) algorithm augmented with two chaotic maps for achieving an improved performance. This FO fuzzy controller shows better performance over the classical PID, and the integer order fuzzy PID controller in both linear and nonlinear operating regimes. The FO fuzzy controller also shows stronger robustness properties against system parameter variation and rate constraint nonlinearity, than that with the other controller structures. The robustness is a highly desirable property in such a scenario since many components of the hybrid power system may be switched on/off or may run at lower/higher power output, at different time instants.
Tasks
Published	2016-11-29
URL	http://arxiv.org/abs/1611.09809v1
PDF	http://arxiv.org/pdf/1611.09809v1.pdf
PWC	https://paperswithcode.com/paper/fractional-order-fuzzy-control-of-hybrid
Repo
Framework

Local and Global Convergence of a General Inertial Proximal Splitting Scheme


Title	Local and Global Convergence of a General Inertial Proximal Splitting Scheme
Authors	Patrick R. Johnstone, Pierre Moulin
Abstract	This paper is concerned with convex composite minimization problems in a Hilbert space. In these problems, the objective is the sum of two closed, proper, and convex functions where one is smooth and the other admits a computationally inexpensive proximal operator. We analyze a general family of inertial proximal splitting algorithms (GIPSA) for solving such problems. We establish finiteness of the sum of squared increments of the iterates and optimality of the accumulation points. Weak convergence of the entire sequence then follows if the minimum is attained. Our analysis unifies and extends several previous results. We then focus on $\ell_1$-regularized optimization, which is the ubiquitous special case where the nonsmooth term is the $\ell_1$-norm. For certain parameter choices, GIPSA is amenable to a local analysis for this problem. For these choices we show that GIPSA achieves finite “active manifold identification”, i.e. convergence in a finite number of iterations to the optimal support and sign, after which GIPSA reduces to minimizing a local smooth function. Local linear convergence then holds under certain conditions. We determine the rate in terms of the inertia, stepsize, and local curvature. Our local analysis is applicable to certain recent variants of the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA), for which we establish active manifold identification and local linear convergence. Our analysis motivates the use of a momentum restart scheme in these FISTA variants to obtain the optimal local linear convergence rate.
Tasks
Published	2016-02-08
URL	http://arxiv.org/abs/1602.02726v1
PDF	http://arxiv.org/pdf/1602.02726v1.pdf
PWC	https://paperswithcode.com/paper/local-and-global-convergence-of-a-general
Repo
Framework

Towards ontology driven learning of visual concept detectors


Title	Towards ontology driven learning of visual concept detectors
Authors	Sanchit Arora, Chuck Cho, Paul Fitzpatrick, Francois Scharffe
Abstract	The maturity of deep learning techniques has led in recent years to a breakthrough in object recognition in visual media. While for some specific benchmarks, neural techniques seem to match if not outperform human judgement, challenges are still open for detecting arbitrary concepts in arbitrary videos. In this paper, we propose a system that combines neural techniques, a large scale visual concepts ontology, and an active learning loop, to provide on the fly model learning of arbitrary concepts. We give an overview of the system as a whole, and focus on the central role of the ontology for guiding and bootstrapping the learning of new concepts, improving the recall of concept detection, and, on the user end, providing semantic search on a library of annotated videos.
Tasks	Active Learning, Object Recognition
Published	2016-05-31
URL	http://arxiv.org/abs/1605.09757v1
PDF	http://arxiv.org/pdf/1605.09757v1.pdf
PWC	https://paperswithcode.com/paper/towards-ontology-driven-learning-of-visual
Repo
Framework