July 26, 2019

3194 words 15 mins read

Paper Group ANR 795

See the Near Future: A Short-Term Predictive Methodology to Traffic Load in ITS. Super-Resolution for Overhead Imagery Using DenseNets and Adversarial Learning. A Multiple Radar Approach for Automatic Target Recognition of Aircraft using Inverse Synthetic Aperture Radar. Combinatorial Multi-armed Bandits for Real-Time Strategy Games. Ignoring Distr …

See the Near Future: A Short-Term Predictive Methodology to Traffic Load in ITS


Title	See the Near Future: A Short-Term Predictive Methodology to Traffic Load in ITS
Authors	Xun Zhou, Changle Li, Zhe Liu, Tom H. Luan, Zhifang Miao, Lina Zhu, Lei Xiong
Abstract	The Intelligent Transportation System (ITS) targets to a coordinated traffic system by applying the advanced wireless communication technologies for road traffic scheduling. Towards an accurate road traffic control, the short-term traffic forecasting to predict the road traffic at the particular site in a short period is often useful and important. In existing works, Seasonal Autoregressive Integrated Moving Average (SARIMA) model is a popular approach. The scheme however encounters two challenges: 1) the analysis on related data is insufficient whereas some important features of data may be neglected; and 2) with data presenting different features, it is unlikely to have one predictive model that can fit all situations. To tackle above issues, in this work, we develop a hybrid model to improve accuracy of SARIMA. In specific, we first explore the autocorrelation and distribution features existed in traffic flow to revise structure of the time series model. Based on the Gaussian distribution of traffic flow, a hybrid model with a Bayesian learning algorithm is developed which can effectively expand the application scenarios of SARIMA. We show the efficiency and accuracy of our proposal using both analysis and experimental studies. Using the real-world trace data, we show that the proposed predicting approach can achieve satisfactory performance in practice.
Tasks	Time Series
Published	2017-01-08
URL	http://arxiv.org/abs/1701.01917v1
PDF	http://arxiv.org/pdf/1701.01917v1.pdf
PWC	https://paperswithcode.com/paper/see-the-near-future-a-short-term-predictive
Repo
Framework

Super-Resolution for Overhead Imagery Using DenseNets and Adversarial Learning


Title	Super-Resolution for Overhead Imagery Using DenseNets and Adversarial Learning
Authors	Marc Bosch, Christopher M. Gifford, Pedro A. Rodriguez
Abstract	Recent advances in Generative Adversarial Learning allow for new modalities of image super-resolution by learning low to high resolution mappings. In this paper we present our work using Generative Adversarial Networks (GANs) with applications to overhead and satellite imagery. We have experimented with several state-of-the-art architectures. We propose a GAN-based architecture using densely connected convolutional neural networks (DenseNets) to be able to super-resolve overhead imagery with a factor of up to 8x. We have also investigated resolution limits of these networks. We report results on several publicly available datasets, including SpaceNet data and IARPA Multi-View Stereo Challenge, and compare performance with other state-of-the-art architectures.
Tasks	Image Super-Resolution, Super-Resolution
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10312v1
PDF	http://arxiv.org/pdf/1711.10312v1.pdf
PWC	https://paperswithcode.com/paper/super-resolution-for-overhead-imagery-using
Repo
Framework

A Multiple Radar Approach for Automatic Target Recognition of Aircraft using Inverse Synthetic Aperture Radar


Title	A Multiple Radar Approach for Automatic Target Recognition of Aircraft using Inverse Synthetic Aperture Radar
Authors	Carlos Pena-Caballero, Elifaleth Cantu, Jesus Rodriguez, Adolfo Gonzales, Osvaldo Castellanos, Angel Cantu, Megan Strait, Jae Son, Dongchul Kim
Abstract	Along with the improvement of radar technologies, Automatic Target Recognition (ATR) using Synthetic Aperture Radar (SAR) and Inverse SAR (ISAR) has come to be an active research area. SAR/ISAR are radar techniques to generate a two-dimensional high-resolution image of a target. Unlike other similar experiments using Convolutional Neural Networks (CNN) to solve this problem, we utilize an unusual approach that leads to better performance and faster training times. Our CNN uses complex values generated by a simulation to train the network; additionally, we utilize a multi-radar approach to increase the accuracy of the training and testing processes, thus resulting in higher accuracies than the other papers working on SAR/ISAR ATR. We generated our dataset with 7 different aircraft models with a radar simulator we developed called RadarPixel; it is a Windows GUI program implemented using Matlab and Java programming, the simulator is capable of accurately replicating a real SAR/ISAR configurations. Our objective is to utilize our multi-radar technique and determine the optimal number of radars needed to detect and classify targets.
Tasks
Published	2017-11-14
URL	http://arxiv.org/abs/1711.04901v2
PDF	http://arxiv.org/pdf/1711.04901v2.pdf
PWC	https://paperswithcode.com/paper/a-multiple-radar-approach-for-automatic
Repo
Framework

Combinatorial Multi-armed Bandits for Real-Time Strategy Games


Title	Combinatorial Multi-armed Bandits for Real-Time Strategy Games
Authors	Santiago Ontañón
Abstract	Games with large branching factors pose a significant challenge for game tree search algorithms. In this paper, we address this problem with a sampling strategy for Monte Carlo Tree Search (MCTS) algorithms called {\em na"{i}ve sampling}, based on a variant of the Multi-armed Bandit problem called {\em Combinatorial Multi-armed Bandits} (CMAB). We analyze the theoretical properties of several variants of {\em na"{i}ve sampling}, and empirically compare it against the other existing strategies in the literature for CMABs. We then evaluate these strategies in the context of real-time strategy (RTS) games, a genre of computer games characterized by their very large branching factors. Our results show that as the branching factor grows, {\em na"{i}ve sampling} outperforms the other sampling strategies.
Tasks	Multi-Armed Bandits, Real-Time Strategy Games
Published	2017-10-13
URL	http://arxiv.org/abs/1710.04805v1
PDF	http://arxiv.org/pdf/1710.04805v1.pdf
PWC	https://paperswithcode.com/paper/combinatorial-multi-armed-bandits-for-real
Repo
Framework

Ignoring Distractors in the Absence of Labels: Optimal Linear Projection to Remove False Positives During Anomaly Detection


Title	Ignoring Distractors in the Absence of Labels: Optimal Linear Projection to Remove False Positives During Anomaly Detection
Authors	Allison Del Giorno, J. Andrew Bagnell, Martial Hebert
Abstract	In the anomaly detection setting, the native feature embedding can be a crucial source of bias. We present a technique, Feature Omission using Context in Unsupervised Settings (FOCUS) to learn a feature mapping that is invariant to changes exemplified in training sets while retaining as much descriptive power as possible. While this method could apply to many unsupervised settings, we focus on applications in anomaly detection, where little task-labeled data is available. Our algorithm requires only non-anomalous sets of data, and does not require that the contexts in the training sets match the context of the test set. By maximizing within-set variance and minimizing between-set variance, we are able to identify and remove distracting features while retaining fidelity to the descriptiveness needed at test time. In the linear case, our formulation reduces to a generalized eigenvalue problem that can be solved quickly and applied to test sets outside the context of the training sets. This technique allows us to align technical definitions of anomaly detection with human definitions through appropriate mappings of the feature space. We demonstrate that this method is able to remove uninformative parts of the feature space for the anomaly detection setting.
Tasks	Anomaly Detection
Published	2017-09-13
URL	http://arxiv.org/abs/1709.04549v1
PDF	http://arxiv.org/pdf/1709.04549v1.pdf
PWC	https://paperswithcode.com/paper/ignoring-distractors-in-the-absence-of-labels
Repo
Framework

Recurrent Latent Variable Networks for Session-Based Recommendation


Title	Recurrent Latent Variable Networks for Session-Based Recommendation
Authors	Sotirios Chatzis, Panayiotis Christodoulou, Andreas S. Andreou
Abstract	In this work, we attempt to ameliorate the impact of data sparsity in the context of session-based recommendation. Specifically, we seek to devise a machine learning mechanism capable of extracting subtle and complex underlying temporal dynamics in the observed session data, so as to inform the recommendation algorithm. To this end, we improve upon systems that utilize deep learning techniques with recurrently connected units; we do so by adopting concepts from the field of Bayesian statistics, namely variational inference. Our proposed approach consists in treating the network recurrent units as stochastic latent variables with a prior distribution imposed over them. On this basis, we proceed to infer corresponding posteriors; these can be used for prediction and recommendation generation, in a way that accounts for the uncertainty in the available sparse training data. To allow for our approach to easily scale to large real-world datasets, we perform inference under an approximate amortized variational inference (AVI) setup, whereby the learned posteriors are parameterized via (conventional) neural networks. We perform an extensive experimental evaluation of our approach using challenging benchmark datasets, and illustrate its superiority over existing state-of-the-art techniques.
Tasks	Session-Based Recommendations
Published	2017-06-13
URL	http://arxiv.org/abs/1706.04026v1
PDF	http://arxiv.org/pdf/1706.04026v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-latent-variable-networks-for
Repo
Framework

Pattern representation and recognition with accelerated analog neuromorphic systems


Title	Pattern representation and recognition with accelerated analog neuromorphic systems
Authors	Mihai A. Petrovici, Sebastian Schmitt, Johann Klähn, David Stöckel, Anna Schroeder, Guillaume Bellec, Johannes Bill, Oliver Breitwieser, Ilja Bytschok, Andreas Grübl, Maurice Güttler, Andreas Hartel, Stephan Hartmann, Dan Husmann, Kai Husmann, Sebastian Jeltsch, Vitali Karasenko, Mitja Kleider, Christoph Koke, Alexander Kononov, Christian Mauch, Eric Müller, Paul Müller, Johannes Partzsch, Thomas Pfeil, Stefan Schiefer, Stefan Scholze, Anand Subramoney, Vasilis Thanasoulis, Bernhard Vogginger, Robert Legenstein, Wolfgang Maass, René Schüffny, Christian Mayr, Johannes Schemmel, Karlheinz Meier
Abstract	Despite being originally inspired by the central nervous system, artificial neural networks have diverged from their biological archetypes as they have been remodeled to fit particular tasks. In this paper, we review several possibilites to reverse map these architectures to biologically more realistic spiking networks with the aim of emulating them on fast, low-power neuromorphic hardware. Since many of these devices employ analog components, which cannot be perfectly controlled, finding ways to compensate for the resulting effects represents a key challenge. Here, we discuss three different strategies to address this problem: the addition of auxiliary network components for stabilizing activity, the utilization of inherently robust architectures and a training method for hardware-emulated networks that functions without perfect knowledge of the system’s dynamics and parameters. For all three scenarios, we corroborate our theoretical considerations with experimental results on accelerated analog neuromorphic platforms.
Tasks
Published	2017-03-17
URL	http://arxiv.org/abs/1703.06043v2
PDF	http://arxiv.org/pdf/1703.06043v2.pdf
PWC	https://paperswithcode.com/paper/pattern-representation-and-recognition-with
Repo
Framework

The Interplay of Semantics and Morphology in Word Embeddings


Title	The Interplay of Semantics and Morphology in Word Embeddings
Authors	Oded Avraham, Yoav Goldberg
Abstract	We explore the ability of word embeddings to capture both semantic and morphological similarity, as affected by the different types of linguistic properties (surface form, lemma, morphological tag) used to compose the representation of each word. We train several models, where each uses a different subset of these properties to compose its representations. By evaluating the models on semantic and morphological measures, we reveal some useful insights on the relationship between semantics and morphology.
Tasks	Word Embeddings
Published	2017-04-06
URL	http://arxiv.org/abs/1704.01938v1
PDF	http://arxiv.org/pdf/1704.01938v1.pdf
PWC	https://paperswithcode.com/paper/the-interplay-of-semantics-and-morphology-in
Repo
Framework

Efficient Multi-Person Pose Estimation with Provable Guarantees


Title	Efficient Multi-Person Pose Estimation with Provable Guarantees
Authors	Shaofei Wang, Konrad Paul Kording, Julian Yarkony
Abstract	Multi-person pose estimation (MPPE) in natural images is key to the meaningful use of visual data in many fields including movement science, security, and rehabilitation. In this paper we tackle MPPE with a bottom-up approach, starting with candidate detections of body parts from a convolutional neural network (CNN) and grouping them into people. We formulate the grouping of body part detections into people as a minimum-weight set packing (MWSP) problem where the set of potential people is the power set of body part detections. We model the quality of a hypothesis of a person which is a set in the MWSP by an augmented tree-structured Markov random field where variables correspond to body-parts and their state-spaces correspond to the power set of the detections for that part. We describe a novel algorithm that combines efficiency with provable bounds on this MWSP problem. We employ an implicit column generation strategy where the pricing problem is formulated as a dynamic program. To efficiently solve this dynamic program we exploit the problem structure utilizing a nested Bender’s decomposition (NBD) exact inference strategy which we speed up by recycling Bender’s rows between calls to the pricing problem. We test our approach on the MPII-Multiperson dataset, showing that our approach obtains comparable results with the state-of-the-art algorithm for joint node labeling and grouping problems, and that NBD achieves considerable speed-ups relative to a naive dynamic programming approach. Typical algorithms that solve joint node labeling and grouping problems use heuristics and thus can not obtain proofs of optimality. Our approach, in contrast, proves that for over 99 percent of problem instances we find the globally optimal solution and otherwise provide upper/lower bounds.
Tasks	Multi-Person Pose Estimation, Pose Estimation
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07794v1
PDF	http://arxiv.org/pdf/1711.07794v1.pdf
PWC	https://paperswithcode.com/paper/efficient-multi-person-pose-estimation-with
Repo
Framework

Deep Gaussian Covariance Network


Title	Deep Gaussian Covariance Network
Authors	Kevin Cremanns, Dirk Roos
Abstract	The correlation length-scale next to the noise variance are the most used hyperparameters for the Gaussian processes. Typically, stationary covariance functions are used, which are only dependent on the distances between input points and thus invariant to the translations in the input space. The optimization of the hyperparameters is commonly done by maximizing the log marginal likelihood. This works quite well, if the distances are uniform distributed. In the case of a locally adapted or even sparse input space, the prediction of a test point can be worse dependent of its position. A possible solution to this, is the usage of a non-stationary covariance function, where the hyperparameters are calculated by a deep neural network. So that the correlation length scales and possibly the noise variance are dependent on the test point. Furthermore, different types of covariance functions are trained simultaneously, so that the Gaussian process prediction is an additive overlay of different covariance matrices. The right covariance functions combination and its hyperparameters are learned by the deep neural network. Additional, the Gaussian process will be able to be trained by batches or online and so it can handle arbitrarily large data sets. We call this framework Deep Gaussian Covariance Network (DGCP). There are also further extensions to this framework possible, for example sequentially dependent problems like time series or the local mixture of experts. The basic framework and some extension possibilities will be presented in this work. Moreover, a comparison to some recent state of the art surrogate model methods will be performed, also for a time dependent problem.
Tasks	Gaussian Processes, Time Series
Published	2017-10-17
URL	http://arxiv.org/abs/1710.06202v2
PDF	http://arxiv.org/pdf/1710.06202v2.pdf
PWC	https://paperswithcode.com/paper/deep-gaussian-covariance-network
Repo
Framework

280 Birds with One Stone: Inducing Multilingual Taxonomies from Wikipedia using Character-level Classification


Title	280 Birds with One Stone: Inducing Multilingual Taxonomies from Wikipedia using Character-level Classification
Authors	Amit Gupta, Rémi Lebret, Hamza Harkous, Karl Aberer
Abstract	We propose a simple, yet effective, approach towards inducing multilingual taxonomies from Wikipedia. Given an English taxonomy, our approach leverages the interlanguage links of Wikipedia followed by character-level classifiers to induce high-precision, high-coverage taxonomies in other languages. Through experiments, we demonstrate that our approach significantly outperforms the state-of-the-art, heuristics-heavy approaches for six languages. As a consequence of our work, we release presumably the largest and the most accurate multilingual taxonomic resource spanning over 280 languages.
Tasks
Published	2017-04-25
URL	http://arxiv.org/abs/1704.07624v2
PDF	http://arxiv.org/pdf/1704.07624v2.pdf
PWC	https://paperswithcode.com/paper/280-birds-with-one-stone-inducing
Repo
Framework

Context-modulation of hippocampal dynamics and deep convolutional networks


Title	Context-modulation of hippocampal dynamics and deep convolutional networks
Authors	James B. Aimone, William M. Severa
Abstract	Complex architectures of biological neural circuits, such as parallel processing pathways, has been behaviorally implicated in many cognitive studies. However, the theoretical consequences of circuit complexity on neural computation have only been explored in limited cases. Here, we introduce a mechanism by which direct and indirect pathways from cortex to the CA3 region of the hippocampus can balance both contextual gating of memory formation and driving network activity. We implement this concept in a deep artificial neural network by enabling a context-sensitive bias. The motivation for this is to improve performance of a size-constrained network. Using direct knowledge of the superclass information in the CIFAR-100 and Fashion-MNIST datasets, we show a dramatic increase in performance without an increase in network size.
Tasks
Published	2017-11-27
URL	http://arxiv.org/abs/1711.09876v1
PDF	http://arxiv.org/pdf/1711.09876v1.pdf
PWC	https://paperswithcode.com/paper/context-modulation-of-hippocampal-dynamics
Repo
Framework

Coresets for Vector Summarization with Applications to Network Graphs


Title	Coresets for Vector Summarization with Applications to Network Graphs
Authors	Dan Feldman, Sedat Ozer, Daniela Rus
Abstract	We provide a deterministic data summarization algorithm that approximates the mean $\bar{p}=\frac{1}{n}\sum_{p\in P} p$ of a set $P$ of $n$ vectors in $\REAL^d$, by a weighted mean $\tilde{p}$ of a \emph{subset} of $O(1/\eps)$ vectors, i.e., independent of both $n$ and $d$. We prove that the squared Euclidean distance between $\bar{p}$ and $\tilde{p}$ is at most $\eps$ multiplied by the variance of $P$. We use this algorithm to maintain an approximated sum of vectors from an unbounded stream, using memory that is independent of $d$, and logarithmic in the $n$ vectors seen so far. Our main application is to extract and represent in a compact way friend groups and activity summaries of users from underlying data exchanges. For example, in the case of mobile networks, we can use GPS traces to identify meetings, in the case of social networks, we can use information exchange to identify friend groups. Our algorithm provably identifies the {\it Heavy Hitter} entries in a proximity (adjacency) matrix. The Heavy Hitters can be used to extract and represent in a compact way friend groups and activity summaries of users from underlying data exchanges. We evaluate the algorithm on several large data sets.
Tasks	Data Summarization
Published	2017-06-17
URL	http://arxiv.org/abs/1706.05554v1
PDF	http://arxiv.org/pdf/1706.05554v1.pdf
PWC	https://paperswithcode.com/paper/coresets-for-vector-summarization-with
Repo
Framework

VisDA: The Visual Domain Adaptation Challenge


Title	VisDA: The Visual Domain Adaptation Challenge
Authors	Xingchao Peng, Ben Usman, Neela Kaushik, Judy Hoffman, Dequan Wang, Kate Saenko
Abstract	We present the 2017 Visual Domain Adaptation (VisDA) dataset and challenge, a large-scale testbed for unsupervised domain adaptation across visual domains. Unsupervised domain adaptation aims to solve the real-world problem of domain shift, where machine learning models trained on one domain must be transferred and adapted to a novel visual domain without additional supervision. The VisDA2017 challenge is focused on the simulation-to-reality shift and has two associated tasks: image classification and image segmentation. The goal in both tracks is to first train a model on simulated, synthetic data in the source domain and then adapt it to perform well on real image data in the unlabeled test domain. Our dataset is the largest one to date for cross-domain object classification, with over 280K images across 12 categories in the combined training, validation and testing domains. The image segmentation dataset is also large-scale with over 30K images across 18 categories in the three domains. We compare VisDA to existing cross-domain adaptation datasets and provide a baseline performance analysis using various domain adaptation models that are currently popular in the field.
Tasks	Domain Adaptation, Image Classification, Object Classification, Semantic Segmentation, Unsupervised Domain Adaptation
Published	2017-10-18
URL	http://arxiv.org/abs/1710.06924v2
PDF	http://arxiv.org/pdf/1710.06924v2.pdf
PWC	https://paperswithcode.com/paper/visda-the-visual-domain-adaptation-challenge
Repo
Framework

Dynamic Weight Alignment for Temporal Convolutional Neural Networks


Title	Dynamic Weight Alignment for Temporal Convolutional Neural Networks
Authors	Brian Kenji Iwana, Seiichi Uchida
Abstract	In this paper, we propose a method of improving temporal Convolutional Neural Networks (CNN) by determining the optimal alignment of weights and inputs using dynamic programming. Conventional CNN convolutions linearly match the shared weights to a window of the input. However, it is possible that there exists a more optimal alignment of weights. Thus, we propose the use of Dynamic Time Warping (DTW) to dynamically align the weights to the input of the convolutional layer. Specifically, the dynamic alignment overcomes issues such as temporal distortion by finding the minimal distance matching of the weights and the inputs under constraints. We demonstrate the effectiveness of the proposed architecture on the Unipen online handwritten digit and character datasets, the UCI Spoken Arabic Digit dataset, and the UCI Activities of Daily Life dataset.
Tasks	Time Series
Published	2017-12-18
URL	http://arxiv.org/abs/1712.06530v6
PDF	http://arxiv.org/pdf/1712.06530v6.pdf
PWC	https://paperswithcode.com/paper/dynamic-weight-alignment-for-temporal
Repo
Framework