May 6, 2019

3198 words 16 mins read

Paper Group ANR 210

Dynamic Principal Component Analysis: Identifying the Relationship between Multiple Air Pollutants. Temporal Logic Programs with Variables. Bayesian Decision Process for Cost-Efficient Dynamic Ranking via Crowdsourcing. Pushing the Limits of Deep CNNs for Pedestrian Detection. Learning Multilayer Channel Features for Pedestrian Detection. CNN-based …

Dynamic Principal Component Analysis: Identifying the Relationship between Multiple Air Pollutants


Title	Dynamic Principal Component Analysis: Identifying the Relationship between Multiple Air Pollutants
Authors	Oleg Melnikov, Loren H. Raun, Katherine B. Ensor
Abstract	The dynamic nature of air quality chemistry and transport makes it difficult to identify the mixture of air pollutants for a region. In this study of air quality in the Houston metropolitan area we apply dynamic principal component analysis (DPCA) to a normalized multivariate time series of daily concentration measurements of five pollutants (O3, CO, NO2, SO2, PM2.5) from January 1, 2009 through December 31, 2011 for each of the 24 hours in a day. The resulting dynamic components are examined by hour across days for the 3 year period. Diurnal and seasonal patterns are revealed underlining times when DPCA performs best and two principal components (PCs) explain most variability in the multivariate series. DPCA is shown to be superior to static principal component analysis (PCA) in discovery of linear relations among transformed pollutant measurements. DPCA captures the time-dependent correlation structure of the underlying pollutants recorded at up to 34 monitoring sites in the region. In winter mornings the first principal component (PC1) (mainly CO and NO2) explains up to 70% of variability. Augmenting with the second principal component (PC2) (mainly driven by SO2) the explained variability rises to 90%. In the afternoon, O3 gains prominence in the second principal component. The seasonal profile of PCs’ contribution to variance loses its distinction in the afternoon, yet cumulatively PC1 and PC2 still explain up to 65% of variability in ambient air data. DPCA provides a strategy for identifying the changing air quality profile for the region studied.
Tasks	Time Series
Published	2016-08-10
URL	http://arxiv.org/abs/1608.03022v1
PDF	http://arxiv.org/pdf/1608.03022v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-principal-component-analysis
Repo
Framework

Temporal Logic Programs with Variables


Title	Temporal Logic Programs with Variables
Authors	Felicidad Aguado, Pedro Cabalar, Martín Diéguez, Gilberto Pérez, Concepción Vidal
Abstract	In this note we consider the problem of introducing variables in temporal logic programs under the formalism of “Temporal Equilibrium Logic” (TEL), an extension of Answer Set Programming (ASP) for dealing with linear-time modal operators. To this aim, we provide a definition of a first-order version of TEL that shares the syntax of first-order Linear-time Temporal Logic (LTL) but has a different semantics, selecting some LTL models we call “temporal stable models”. Then, we consider a subclass of theories (called “splittable temporal logic programs”) that are close to usual logic programs but allowing a restricted use of temporal operators. In this setting, we provide a syntactic definition of “safe variables” that suffices to show the property of “domain independence” – that is, addition of arbitrary elements in the universe does not vary the set of temporal stable models. Finally, we present a method for computing the derivable facts by constructing a non-temporal logic program with variables that is fed to a standard ASP grounder. The information provided by the grounder is then used to generate a subset of ground temporal rules which is equivalent to (and generally smaller than) the full program instantiation.
Tasks
Published	2016-09-19
URL	http://arxiv.org/abs/1609.05811v1
PDF	http://arxiv.org/pdf/1609.05811v1.pdf
PWC	https://paperswithcode.com/paper/temporal-logic-programs-with-variables
Repo
Framework

Bayesian Decision Process for Cost-Efficient Dynamic Ranking via Crowdsourcing


Title	Bayesian Decision Process for Cost-Efficient Dynamic Ranking via Crowdsourcing
Authors	Xi Chen, Kevin Jiao, Qihang Lin
Abstract	Rank aggregation based on pairwise comparisons over a set of items has a wide range of applications. Although considerable research has been devoted to the development of rank aggregation algorithms, one basic question is how to efficiently collect a large amount of high-quality pairwise comparisons for the ranking purpose. Because of the advent of many crowdsourcing services, a crowd of workers are often hired to conduct pairwise comparisons with a small monetary reward for each pair they compare. Since different workers have different levels of reliability and different pairs have different levels of ambiguity, it is desirable to wisely allocate the limited budget for comparisons among the pairs of items and workers so that the global ranking can be accurately inferred from the comparison results. To this end, we model the active sampling problem in crowdsourced ranking as a Bayesian Markov decision process, which dynamically selects item pairs and workers to improve the ranking accuracy under a budget constraint. We further develop a computationally efficient sampling policy based on knowledge gradient as well as a moment matching technique for posterior approximation. Experimental evaluations on both synthetic and real data show that the proposed policy achieves high ranking accuracy with a lower labeling cost.
Tasks
Published	2016-12-21
URL	http://arxiv.org/abs/1612.07222v1
PDF	http://arxiv.org/pdf/1612.07222v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-decision-process-for-cost-efficient
Repo
Framework

Pushing the Limits of Deep CNNs for Pedestrian Detection


Title	Pushing the Limits of Deep CNNs for Pedestrian Detection
Authors	Qichang Hu, Peng Wang, Chunhua Shen, Anton van den Hengel, Fatih Porikli
Abstract	Compared to other applications in computer vision, convolutional neural networks have under-performed on pedestrian detection. A breakthrough was made very recently by using sophisticated deep CNN models, with a number of hand-crafted features, or explicit occlusion handling mechanism. In this work, we show that by re-using the convolutional feature maps (CFMs) of a deep convolutional neural network (DCNN) model as image features to train an ensemble of boosted decision models, we are able to achieve the best reported accuracy without using specially designed learning algorithms. We empirically identify and disclose important implementation details. We also show that pixel labelling may be simply combined with a detector to boost the detection performance. By adding complementary hand-crafted features such as optical flow, the DCNN based detector can be further improved. We set a new record on the Caltech pedestrian dataset, lowering the log-average miss rate from $11.7%$ to $8.9%$, a relative improvement of $24%$. We also achieve a comparable result to the state-of-the-art approaches on the KITTI dataset.
Tasks	Optical Flow Estimation, Pedestrian Detection
Published	2016-03-15
URL	http://arxiv.org/abs/1603.04525v2
PDF	http://arxiv.org/pdf/1603.04525v2.pdf
PWC	https://paperswithcode.com/paper/pushing-the-limits-of-deep-cnns-for
Repo
Framework

Learning Multilayer Channel Features for Pedestrian Detection


Title	Learning Multilayer Channel Features for Pedestrian Detection
Authors	Jiale Cao, Yanwei Pang, Xuelong Li
Abstract	Pedestrian detection based on the combination of Convolutional Neural Network (i.e., CNN) and traditional handcrafted features (i.e., HOG+LUV) has achieved great success. Generally, HOG+LUV are used to generate the candidate proposals and then CNN classifies these proposals. Despite its success, there is still room for improvement. For example, CNN classifies these proposals by the full-connected layer features while proposal scores and the features in the inner-layers of CNN are ignored. In this paper, we propose a unifying framework called Multilayer Channel Features (MCF) to overcome the drawback. It firstly integrates HOG+LUV with each layer of CNN into a multi-layer image channels. Based on the multi-layer image channels, a multi-stage cascade AdaBoost is then learned. The weak classifiers in each stage of the multi-stage cascade is learned from the image channels of corresponding layer. With more abundant features, MCF achieves the state-of-the-art on Caltech pedestrian dataset (i.e., 10.40% miss rate). Using new and accurate annotations, MCF achieves 7.98% miss rate. As many non-pedestrian detection windows can be quickly rejected by the first few stages, it accelerates detection speed by 1.43 times. By eliminating the highly overlapped detection windows with lower scores after the first stage, it’s 4.07 times faster with negligible performance loss.
Tasks	Pedestrian Detection
Published	2016-03-01
URL	http://arxiv.org/abs/1603.00124v1
PDF	http://arxiv.org/pdf/1603.00124v1.pdf
PWC	https://paperswithcode.com/paper/learning-multilayer-channel-features-for
Repo
Framework

CNN-based Patch Matching for Optical Flow with Thresholded Hinge Embedding Loss


Title	CNN-based Patch Matching for Optical Flow with Thresholded Hinge Embedding Loss
Authors	Christian Bailer, Kiran Varanasi, Didier Stricker
Abstract	Learning based approaches have not yet achieved their full potential in optical flow estimation, where their performance still trails heuristic approaches. In this paper, we present a CNN based patch matching approach for optical flow estimation. An important contribution of our approach is a novel thresholded loss for Siamese networks. We demonstrate that our loss performs clearly better than existing losses. It also allows to speed up training by a factor of 2 in our tests. Furthermore, we present a novel way for calculating CNN based features for different image scales, which performs better than existing methods. We also discuss new ways of evaluating the robustness of trained features for the application of patch matching for optical flow. An interesting discovery in our paper is that low-pass filtering of feature maps can increase the robustness of features created by CNNs. We proved the competitive performance of our approach by submitting it to the KITTI 2012, KITTI 2015 and MPI-Sintel evaluation portals where we obtained state-of-the-art results on all three datasets.
Tasks	Optical Flow Estimation
Published	2016-07-27
URL	http://arxiv.org/abs/1607.08064v3
PDF	http://arxiv.org/pdf/1607.08064v3.pdf
PWC	https://paperswithcode.com/paper/cnn-based-patch-matching-for-optical-flow
Repo
Framework

Visual Saliency Based on Scale-Space Analysis in the Frequency Domain


Title	Visual Saliency Based on Scale-Space Analysis in the Frequency Domain
Authors	Jian Li, Martin Levine, Xiangjing An, Xin Xu, Hangen He
Abstract	We address the issue of visual saliency from three perspectives. First, we consider saliency detection as a frequency domain analysis problem. Second, we achieve this by employing the concept of {\it non-saliency}. Third, we simultaneously consider the detection of salient regions of different size. The paper proposes a new bottom-up paradigm for detecting visual saliency, characterized by a scale-space analysis of the amplitude spectrum of natural images. We show that the convolution of the {\it image amplitude spectrum} with a low-pass Gaussian kernel of an appropriate scale is equivalent to such an image saliency detector. The saliency map is obtained by reconstructing the 2-D signal using the original phase and the amplitude spectrum, filtered at a scale selected by minimizing saliency map entropy. A Hypercomplex Fourier Transform performs the analysis in the frequency domain. Using available databases, we demonstrate experimentally that the proposed model can predict human fixation data. We also introduce a new image database and use it to show that the saliency detector can highlight both small and large salient regions, as well as inhibit repeated distractors in cluttered images. In addition, we show that it is able to predict salient regions on which people focus their attention.
Tasks	Saliency Detection
Published	2016-05-06
URL	http://arxiv.org/abs/1605.01999v1
PDF	http://arxiv.org/pdf/1605.01999v1.pdf
PWC	https://paperswithcode.com/paper/visual-saliency-based-on-scale-space-analysis
Repo
Framework

Dialogue manager domain adaptation using Gaussian process reinforcement learning


Title	Dialogue manager domain adaptation using Gaussian process reinforcement learning
Authors	Milica Gasic, Nikola Mrksic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve Young
Abstract	Spoken dialogue systems allow humans to interact with machines using natural speech. As such, they have many benefits. By using speech as the primary communication medium, a computer interface can facilitate swift, human-like acquisition of information. In recent years, speech interfaces have become ever more popular, as is evident from the rise of personal assistants such as Siri, Google Now, Cortana and Amazon Alexa. Recently, data-driven machine learning methods have been applied to dialogue modelling and the results achieved for limited-domain applications are comparable to or outperform traditional approaches. Methods based on Gaussian processes are particularly effective as they enable good models to be estimated from limited training data. Furthermore, they provide an explicit estimate of the uncertainty which is particularly useful for reinforcement learning. This article explores the additional steps that are necessary to extend these methods to model multiple dialogue domains. We show that Gaussian process reinforcement learning is an elegant framework that naturally supports a range of methods, including prior knowledge, Bayesian committee machines and multi-agent learning, for facilitating extensible and adaptable dialogue systems.
Tasks	Domain Adaptation, Gaussian Processes, Spoken Dialogue Systems
Published	2016-09-09
URL	http://arxiv.org/abs/1609.02846v1
PDF	http://arxiv.org/pdf/1609.02846v1.pdf
PWC	https://paperswithcode.com/paper/dialogue-manager-domain-adaptation-using
Repo
Framework

Training Deep Spiking Neural Networks using Backpropagation


Title	Training Deep Spiking Neural Networks using Backpropagation
Authors	Jun Haeng Lee, Tobi Delbruck, Michael Pfeiffer
Abstract	Deep spiking neural networks (SNNs) hold great potential for improving the latency and energy efficiency of deep neural networks through event-based computation. However, training such networks is difficult due to the non-differentiable nature of asynchronous spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are only considered as noise. This enables an error backpropagation mechanism for deep SNNs, which works directly on spike signals and membrane potentials. Thus, compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statics of spikes more precisely. Our novel framework outperforms all previously reported results for SNNs on the permutation invariant MNIST benchmark, as well as the N-MNIST benchmark recorded with event-based vision sensors.
Tasks	Event-based vision
Published	2016-08-31
URL	http://arxiv.org/abs/1608.08782v1
PDF	http://arxiv.org/pdf/1608.08782v1.pdf
PWC	https://paperswithcode.com/paper/training-deep-spiking-neural-networks-using
Repo
Framework

EM Algorithm and Stochastic Control in Economics


Title	EM Algorithm and Stochastic Control in Economics
Authors	Steven Kou, Xianhua Peng, Xingbo Xu
Abstract	Generalising the idea of the classical EM algorithm that is widely used for computing maximum likelihood estimates, we propose an EM-Control (EM-C) algorithm for solving multi-period finite time horizon stochastic control problems. The new algorithm sequentially updates the control policies in each time period using Monte Carlo simulation in a forward-backward manner; in other words, the algorithm goes forward in simulation and backward in optimization in each iteration. Similar to the EM algorithm, the EM-C algorithm has the monotonicity of performance improvement in each iteration, leading to good convergence properties. We demonstrate the effectiveness of the algorithm by solving stochastic control problems in the monopoly pricing of perishable assets and in the study of real business cycle.
Tasks
Published	2016-11-06
URL	http://arxiv.org/abs/1611.01767v1
PDF	http://arxiv.org/pdf/1611.01767v1.pdf
PWC	https://paperswithcode.com/paper/em-algorithm-and-stochastic-control-in
Repo
Framework

Graph-Based Manifold Frequency Analysis for Denoising


Title	Graph-Based Manifold Frequency Analysis for Denoising
Authors	Shay Deutsch, Antonio Ortega, Gerard Medioni
Abstract	We propose a new framework for manifold denoising based on processing in the graph Fourier frequency domain, derived from the spectral decomposition of the discrete graph Laplacian. Our approach uses the Spectral Graph Wavelet transform in order to per- form non-iterative denoising directly in the graph frequency domain, an approach inspired by conventional wavelet-based signal denoising methods. We theoretically justify our approach, based on the fact that for smooth manifolds the coordinate information energy is localized in the low spectral graph wavelet sub-bands, while the noise affects all frequency bands in a similar way. Experimental results show that our proposed manifold frequency denoising (MFD) approach significantly outperforms the state of the art denoising meth- ods, and is robust to a wide range of parameter selections, e.g., the choice of k nearest neighbor connectivity of the graph.
Tasks	Denoising
Published	2016-11-29
URL	http://arxiv.org/abs/1611.09510v1
PDF	http://arxiv.org/pdf/1611.09510v1.pdf
PWC	https://paperswithcode.com/paper/graph-based-manifold-frequency-analysis-for
Repo
Framework

A probabilistic graphical model approach in 30 m land cover mapping with multiple data sources


Title	A probabilistic graphical model approach in 30 m land cover mapping with multiple data sources
Authors	Jie Wang, Luyan Ji, Xiaomeng Huang, Haohuan Fu, Shiming Xu, Congcong Li
Abstract	There is a trend to acquire high accuracy land-cover maps using multi-source classification methods, most of which are based on data fusion, especially pixel- or feature-level fusions. A probabilistic graphical model (PGM) approach is proposed in this research for 30 m resolution land-cover mapping with multi-temporal Landsat and MODerate Resolution Imaging Spectroradiometer (MODIS) data. Independent classifiers were applied to two single-date Landsat 8 scenes and the MODIS time-series data, respectively, for probability estimation. A PGM was created for each pixel in Landsat 8 data. Conditional probability distributions were computed based on data quality and reliability by using information selectively. Using the administrative territory of Beijing City (Area-1) and a coastal region of Shandong province, China (Area-2) as study areas, multiple land-cover maps were generated for comparison. Quantitative results show the effectiveness of the proposed method. Overall accuracies promoted from 74.0% (maps acquired from single-temporal Landsat images) to 81.8% (output of the PGM) for Area-1. Improvements can also be seen when using MODIS data and only a single-temporal Landsat image as input (overall accuracy: 78.4% versus 74.0% for Area-1, and 86.8% versus 83.0% for Area-2). Information from MODIS data did not help much when the PGM was applied to cloud free regions of. One of the advantages of the proposed method is that it can be applied where multi-temporal data cannot be simply stacked as a multi-layered image.
Tasks	Time Series
Published	2016-12-11
URL	http://arxiv.org/abs/1612.03373v1
PDF	http://arxiv.org/pdf/1612.03373v1.pdf
PWC	https://paperswithcode.com/paper/a-probabilistic-graphical-model-approach-in
Repo
Framework

Learning Multiscale Features Directly From Waveforms


Title	Learning Multiscale Features Directly From Waveforms
Authors	Zhenyao Zhu, Jesse H. Engel, Awni Hannun
Abstract	Deep learning has dramatically improved the performance of speech recognition systems through learning hierarchies of features optimized for the task at hand. However, true end-to-end learning, where features are learned directly from waveforms, has only recently reached the performance of hand-tailored representations based on the Fourier transform. In this paper, we detail an approach to use convolutional filters to push past the inherent tradeoff of temporal and frequency resolution that exists for spectral representations. At increased computational cost, we show that increasing temporal resolution via reduced stride and increasing frequency resolution via additional filters delivers significant performance improvements. Further, we find more efficient representations by simultaneously learning at multiple scales, leading to an overall decrease in word error rate on a difficult internal speech test set by 20.7% relative to networks with the same number of parameters trained on spectrograms.
Tasks	Speech Recognition
Published	2016-03-31
URL	http://arxiv.org/abs/1603.09509v2
PDF	http://arxiv.org/pdf/1603.09509v2.pdf
PWC	https://paperswithcode.com/paper/learning-multiscale-features-directly-from
Repo
Framework

Combinatorial Multi-Armed Bandit with General Reward Functions


Title	Combinatorial Multi-Armed Bandit with General Reward Functions
Authors	Wei Chen, Wei Hu, Fu Li, Jian Li, Yu Liu, Pinyan Lu
Abstract	In this paper, we study the stochastic combinatorial multi-armed bandit (CMAB) framework that allows a general nonlinear reward function, whose expected value may not depend only on the means of the input random variables but possibly on the entire distributions of these variables. Our framework enables a much larger class of reward functions such as the $\max()$ function and nonlinear utility functions. Existing techniques relying on accurate estimations of the means of random variables, such as the upper confidence bound (UCB) technique, do not work directly on these functions. We propose a new algorithm called stochastically dominant confidence bound (SDCB), which estimates the distributions of underlying random variables and their stochastically dominant confidence bounds. We prove that SDCB can achieve $O(\log{T})$ distribution-dependent regret and $\tilde{O}(\sqrt{T})$ distribution-independent regret, where $T$ is the time horizon. We apply our results to the $K$-MAX problem and expected utility maximization problems. In particular, for $K$-MAX, we provide the first polynomial-time approximation scheme (PTAS) for its offline problem, and give the first $\tilde{O}(\sqrt T)$ bound on the $(1-\epsilon)$-approximation regret of its online problem, for any $\epsilon>0$.
Tasks
Published	2016-10-20
URL	http://arxiv.org/abs/1610.06603v4
PDF	http://arxiv.org/pdf/1610.06603v4.pdf
PWC	https://paperswithcode.com/paper/combinatorial-multi-armed-bandit-with-general
Repo
Framework

Towards Verified Artificial Intelligence


Title	Towards Verified Artificial Intelligence
Authors	Sanjit A. Seshia, Dorsa Sadigh, S. Shankar Sastry
Abstract	Verified artificial intelligence (AI) is the goal of designing AI-based systems that are provably correct with respect to mathematically-specified requirements. This paper considers Verified AI from a formal methods perspective. We describe five challenges for achieving Verified AI, and five corresponding principles for addressing these challenges.
Tasks
Published	2016-06-27
URL	http://arxiv.org/abs/1606.08514v3
PDF	http://arxiv.org/pdf/1606.08514v3.pdf
PWC	https://paperswithcode.com/paper/towards-verified-artificial-intelligence
Repo
Framework