October 20, 2019

3329 words 16 mins read

Paper Group ANR 88

SConE: Siamese Constellation Embedding Descriptor for Image Matching. Visualization of Hyperspectral Images Using Moving Least Squares. Structured Local Optima in Sparse Blind Deconvolution. Doubly Stochastic Adversarial Autoencoder. Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems. The Relevance of Bayesian Layer P …

SConE: Siamese Constellation Embedding Descriptor for Image Matching


Title	SConE: Siamese Constellation Embedding Descriptor for Image Matching
Authors	Tomasz Trzcinski, Jacek Komorowski, Lukasz Dabala, Konrad Czarnota, Grzegorz Kurzejamski, Simon Lynen
Abstract	Numerous computer vision applications rely on local feature descriptors, such as SIFT, SURF or FREAK, for image matching. Although their local character makes image matching processes more robust to occlusions, it often leads to geometrically inconsistent keypoint matches that need to be filtered out, e.g. using RANSAC. In this paper we propose a novel, more discriminative, descriptor that includes not only local feature representation, but also information about the geometric layout of neighbouring keypoints. To that end, we use a Siamese architecture that learns a low-dimensional feature embedding of keypoint constellation by maximizing the distances between non-corresponding pairs of matched image patches, while minimizing it for correct matches. The 48-dimensional oating point descriptor that we train is built on top of the state-of-the-art FREAK descriptor achieves significant performance improvement over the competitors on a challenging TUM dataset.
Tasks
Published	2018-09-28
URL	http://arxiv.org/abs/1809.11054v1
PDF	http://arxiv.org/pdf/1809.11054v1.pdf
PWC	https://paperswithcode.com/paper/scone-siamese-constellation-embedding
Repo
Framework

Visualization of Hyperspectral Images Using Moving Least Squares


Title	Visualization of Hyperspectral Images Using Moving Least Squares
Authors	Danping Liao, Siyu Chen, Yuntao Qian
Abstract	Displaying the large number of bands in a hyper spectral image on a trichromatic monitor has been an active research topic. The visualized image shall convey as much information as possible form the original data and facilitate image interpretation. Most existing methods display HSIs in false colors which contradict with human’s experience and expectation. In this paper, we propose a nonlinear approach to visualize an input HSI with natural colors by taking advantage of a corresponding RGB image. Our approach is based on Moving Least Squares, an interpolation scheme for reconstructing a surface from a set of control points, which in our case is a set of matching pixels between the HSI and the corresponding RGB image. Based on MLS, the proposed method solves for each spectral signature a unique transformation so that the non linear structure of the HSI can be preserved. The matching pixels between a pair of HSI and RGB image can be reused to display other HSIs captured b the same imaging sensor with natural colors. Experiments show that the output image of the proposed method no only have natural colors but also maintain the visual information necessary for human analysis.
Tasks
Published	2018-01-20
URL	http://arxiv.org/abs/1801.06635v1
PDF	http://arxiv.org/pdf/1801.06635v1.pdf
PWC	https://paperswithcode.com/paper/visualization-of-hyperspectral-images-using
Repo
Framework


Title	Structured Local Optima in Sparse Blind Deconvolution
Authors	Yuqian Zhang, Han-Wen Kuo, John Wright
Abstract	Blind deconvolution is a ubiquitous problem of recovering two unknown signals from their convolution. Unfortunately, this is an ill-posed problem in general. This paper focuses on the {\em short and sparse} blind deconvolution problem, where the one unknown signal is short and the other one is sparsely and randomly supported. This variant captures the structure of the unknown signals in several important applications. We assume the short signal to have unit $\ell^2$ norm and cast the blind deconvolution problem as a nonconvex optimization problem over the sphere. We demonstrate that (i) in a certain region of the sphere, every local optimum is close to some shift truncation of the ground truth, and (ii) for a generic short signal of length $k$, when the sparsity of activation signal $\theta\lesssim k^{-2/3}$ and number of measurements $m\gtrsim poly(k)$, a simple initialization method together with a descent algorithm which escapes strict saddle points recovers a near shift truncation of the ground truth kernel.
Tasks
Published	2018-06-01
URL	https://arxiv.org/abs/1806.00338v2
PDF	https://arxiv.org/pdf/1806.00338v2.pdf
PWC	https://paperswithcode.com/paper/structured-local-optima-in-sparse-blind
Repo
Framework

Doubly Stochastic Adversarial Autoencoder


Title	Doubly Stochastic Adversarial Autoencoder
Authors	Mahdi Azarafrooz
Abstract	Any autoencoder network can be turned into a generative model by imposing an arbitrary prior distribution on its hidden code vector. Variational Autoencoder (VAE) [2] uses a KL divergence penalty to impose the prior, whereas Adversarial Autoencoder (AAE) [1] uses {\it generative adversarial networks} GAN [3]. GAN trades the complexities of {\it sampling} algorithms with the complexities of {\it searching} Nash equilibrium in minimax games. Such minimax architectures get trained with the help of data examples and gradients flowing through a generator and an adversary. A straightforward modification of AAE is to replace the adversary with the maximum mean discrepancy (MMD) test [4-5]. This replacement leads to a new type of probabilistic autoencoder, which is also discussed in our paper. We propose a novel probabilistic autoencoder in which the adversary of AAE is replaced with a space of {\it stochastic} functions. This replacement introduces a new source of randomness, which can be considered as a continuous control for encouraging {\it explorations}. This prevents the adversary from fitting too closely to the generator and therefore leads to a more diverse set of generated samples.
Tasks	Continuous Control
Published	2018-07-19
URL	http://arxiv.org/abs/1807.07603v1
PDF	http://arxiv.org/pdf/1807.07603v1.pdf
PWC	https://paperswithcode.com/paper/doubly-stochastic-adversarial-autoencoder
Repo
Framework

Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems


Title	Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems
Authors	Rahul Goel, Shachi Paul, Tagyoung Chung, Jeremie Lecomte, Arindam Mandal, Dilek Hakkani-Tur
Abstract	Goal-oriented dialogue systems typically rely on components specifically developed for a single task or domain. This limits such systems in two different ways: If there is an update in the task domain, the dialogue system usually needs to be updated or completely re-trained. It is also harder to extend such dialogue systems to different and multiple domains. The dialogue state tracker in conventional dialogue systems is one such component - it is usually designed to fit a well-defined application domain. For example, it is common for a state variable to be a categorical distribution over a manually-predefined set of entities (Henderson et al., 2013), resulting in an inflexible and hard-to-extend dialogue system. In this paper, we propose a new approach for dialogue state tracking that can generalize well over multiple domains without incorporating any domain-specific knowledge. Under this framework, discrete dialogue state variables are learned independently and the information of a predefined set of possible values for dialogue state variables is not required. Furthermore, it enables adding arbitrary dialogue context as features and allows for multiple values to be associated with a single state variable. These characteristics make it much easier to expand the dialogue state space. We evaluate our framework using the widely used dialogue state tracking challenge data set (DSTC2) and show that our framework yields competitive results with other state-of-the-art results despite incorporating little domain knowledge. We also show that this framework can benefit from widely available external resources such as pre-trained word embeddings.
Tasks	Dialogue State Tracking, Goal-Oriented Dialogue Systems, Word Embeddings
Published	2018-11-30
URL	http://arxiv.org/abs/1811.12891v1
PDF	http://arxiv.org/pdf/1811.12891v1.pdf
PWC	https://paperswithcode.com/paper/flexible-and-scalable-state-tracking
Repo
Framework

The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning


Title	The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning
Authors	Jiaming Zeng, Adam Lesnikowski, Jose M. Alvarez
Abstract	One of the main challenges of deep learning tools is their inability to capture model uncertainty. While Bayesian deep learning can be used to tackle the problem, Bayesian neural networks often require more time and computational power to train than deterministic networks. Our work explores whether fully Bayesian networks are needed to successfully capture model uncertainty. We vary the number and position of Bayesian layers in a network and compare their performance on active learning with the MNIST dataset. We found that we can fully capture the model uncertainty by using only a few Bayesian layers near the output of the network, combining the advantages of deterministic and Bayesian networks.
Tasks	Active Learning
Published	2018-11-29
URL	http://arxiv.org/abs/1811.12535v1
PDF	http://arxiv.org/pdf/1811.12535v1.pdf
PWC	https://paperswithcode.com/paper/the-relevance-of-bayesian-layer-positioning
Repo
Framework

Anomaly Detection Models for IoT Time Series Data


Title	Anomaly Detection Models for IoT Time Series Data
Authors	Federico Giannoni, Marco Mancini, Federico Marinelli
Abstract	Insitu sensors and Wireless Sensor Networks (WSNs) have become more and more popular in the last decade, due to their potential to be used in various applications of many different fields. As of today, WSNs are pretty much used by any monitoring system: from those that are health care related, to those that are used for environmental forecasting or surveillance purposes. All applications that make use of insitu sensors, strongly rely on their correct operation, which however, is quite difficult to guarantee. These sensors in fact, are typically cheap and prone to malfunction. Additionally, for many tasks (e.g. environmental forecasting), sensors are also deployed under potentially harsh weather condition, making their breakage even more likely. The high probability of erroneous readings or data corruption during transmission, brings up the problem of ensuring quality of the data collected by sensors. Since WSNs have to operate continuously and therefore generate very large volumes of data every day, the quality control process has to be automated, scalable and fast enough to be applicable to streaming data. The most common approach to ensure the quality of sensors data, consists in automated detection of erroneous readings or anomalous behaviours of sensors. In the literature, this strategy is known as anomaly detection and can be pursued in many different ways.
Tasks	Anomaly Detection, Time Series
Published	2018-11-30
URL	http://arxiv.org/abs/1812.00890v1
PDF	http://arxiv.org/pdf/1812.00890v1.pdf
PWC	https://paperswithcode.com/paper/anomaly-detection-models-for-iot-time-series
Repo
Framework

Rigorous Restricted Isometry Property of Low-Dimensional Subspaces


Title	Rigorous Restricted Isometry Property of Low-Dimensional Subspaces
Authors	Gen Li, Qinghua Liu, Yuantao Gu
Abstract	Dimensionality reduction is in demand to reduce the complexity of solving large-scale problems with data lying in latent low-dimensional structures in machine learning and computer version. Motivated by such need, in this work we study the Restricted Isometry Property (RIP) of Gaussian random projections for low-dimensional subspaces in $\mathbb{R}^N$, and rigorously prove that the projection Frobenius norm distance between any two subspaces spanned by the projected data in $\mathbb{R}^n$ ($n<N$) remain almost the same as the distance between the original subspaces with probability no less than $1 - {\rm e}^{-\mathcal{O}(n)}$. Previously the well-known Johnson-Lindenstrauss (JL) Lemma and RIP for sparse vectors have been the foundation of sparse signal processing including Compressed Sensing. As an analogy to JL Lemma and RIP for sparse vectors, this work allows the use of random projections to reduce the ambient dimension with the theoretical guarantee that the distance between subspaces after compression is well preserved.
Tasks	Dimensionality Reduction
Published	2018-01-30
URL	http://arxiv.org/abs/1801.10058v1
PDF	http://arxiv.org/pdf/1801.10058v1.pdf
PWC	https://paperswithcode.com/paper/rigorous-restricted-isometry-property-of-low
Repo
Framework

Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs


Title	Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs
Authors	Miguel Lázaro-Gredilla, Dianhuan Lin, J. Swaroop Guntupalli, Dileep George
Abstract	Humans can infer concepts from image pairs and apply those in the physical world in a completely different setting, enabling tasks like IKEA assembly from diagrams. If robots could represent and infer high-level concepts, it would significantly improve their ability to understand our intent and to transfer tasks between different environments. To that end, we introduce a computational framework that replicates aspects of human concept learning. Concepts are represented as programs on a novel computer architecture consisting of a visual perception system, working memory, and action controller. The instruction set of this “cognitive computer” has commands for parsing a visual scene, directing gaze and attention, imagining new objects, manipulating the contents of a visual working memory, and controlling arm movement. Inferring a concept corresponds to inducing a program that can transform the input to the output. Some concepts require the use of imagination and recursion. Previously learned concepts simplify the learning of subsequent more elaborate concepts, and create a hierarchy of abstractions. We demonstrate how a robot can use these abstractions to interpret novel concepts presented to it as schematic images, and then apply those concepts in dramatically different situations. By bringing cognitive science ideas on mental imagery, perceptual symbols, embodied cognition, and deictic mechanisms into the realm of machine learning, our work brings us closer to the goal of building robots that have interpretable representations and commonsense.
Tasks
Published	2018-12-06
URL	http://arxiv.org/abs/1812.02788v1
PDF	http://arxiv.org/pdf/1812.02788v1.pdf
PWC	https://paperswithcode.com/paper/beyond-imitation-zero-shot-task-transfer-on
Repo
Framework

A Multi-perspective Approach To Anomaly Detection For Self-aware Embodied Agents


Title	A Multi-perspective Approach To Anomaly Detection For Self-aware Embodied Agents
Authors	Mohamad Baydoun, Mahdyar Ravanbakhsh, Damian Campo, Pablo Marin, David Martin, Lucio Marcenaro, Andrea Cavallaro, Carlo S. Regazzoni
Abstract	This paper focuses on multi-sensor anomaly detection for moving cognitive agents using both external and private first-person visual observations. Both observation types are used to characterize agents’ motion in a given environment. The proposed method generates locally uniform motion models by dividing a Gaussian process that approximates agents’ displacements on the scene and provides a Shared Level (SL) self-awareness based on Environment Centered (EC) models. Such models are then used to train in a semi-unsupervised way a set of Generative Adversarial Networks (GANs) that produce an estimation of external and internal parameters of moving agents. Obtained results exemplify the feasibility of using multi-perspective data for predicting and analyzing trajectory information.
Tasks	Anomaly Detection
Published	2018-03-17
URL	http://arxiv.org/abs/1803.06579v1
PDF	http://arxiv.org/pdf/1803.06579v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-perspective-approach-to-anomaly
Repo
Framework

Deception in Optimal Control


Title	Deception in Optimal Control
Authors	Melkior Ornik, Ufuk Topcu
Abstract	In this paper, we consider an adversarial scenario where one agent seeks to achieve an objective and its adversary seeks to learn the agent’s intentions and prevent the agent from achieving its objective. The agent has an incentive to try to deceive the adversary about its intentions, while at the same time working to achieve its objective. The primary contribution of this paper is to introduce a mathematically rigorous framework for the notion of deception within the context of optimal control. The central notion introduced in the paper is that of a belief-induced reward: a reward dependent not only on the agent’s state and action, but also adversary’s beliefs. Design of an optimal deceptive strategy then becomes a question of optimal control design on the product of the agent’s state space and the adversary’s belief space. The proposed framework allows for deception to be defined in an arbitrary control system endowed with a reward function, as well as with additional specifications limiting the agent’s control policy. In addition to defining deception, we discuss design of optimally deceptive strategies under uncertainties in agent’s knowledge about the adversary’s learning process. In the latter part of the paper, we focus on a setting where the agent’s behavior is governed by a Markov decision process, and show that the design of optimally deceptive strategies under lack of knowledge about the adversary naturally reduces to previously discussed problems in control design on partially observable or uncertain Markov decision processes. Finally, we present two examples of deceptive strategies: a “cops and robbers” scenario and an example where an agent may use camouflage while moving. We show that optimally deceptive strategies in such examples follow the intuitive idea of how to deceive an adversary in the above settings.
Tasks
Published	2018-05-08
URL	http://arxiv.org/abs/1805.03090v1
PDF	http://arxiv.org/pdf/1805.03090v1.pdf
PWC	https://paperswithcode.com/paper/deception-in-optimal-control
Repo
Framework

Gauged Mini-Bucket Elimination for Approximate Inference


Title	Gauged Mini-Bucket Elimination for Approximate Inference
Authors	Sungsoo Ahn, Michael Chertkov, Jinwoo Shin, Adrian Weller
Abstract	Computing the partition function $Z$ of a discrete graphical model is a fundamental inference challenge. Since this is computationally intractable, variational approximations are often used in practice. Recently, so-called gauge transformations were used to improve variational lower bounds on $Z$. In this paper, we propose a new gauge-variational approach, termed WMBE-G, which combines gauge transformations with the weighted mini-bucket elimination (WMBE) method. WMBE-G can provide both upper and lower bounds on $Z$, and is easier to optimize than the prior gauge-variational algorithm. We show that WMBE-G strictly improves the earlier WMBE approximation for symmetric models including Ising models with no magnetic field. Our experimental results demonstrate the effectiveness of WMBE-G even for generic, nonsymmetric models.
Tasks
Published	2018-01-05
URL	http://arxiv.org/abs/1801.01649v2
PDF	http://arxiv.org/pdf/1801.01649v2.pdf
PWC	https://paperswithcode.com/paper/gauged-mini-bucket-elimination-for
Repo
Framework

Beyond the Click-Through Rate: Web Link Selection with Multi-level Feedback


Title	Beyond the Click-Through Rate: Web Link Selection with Multi-level Feedback
Authors	Kun Chen, Kechao Cai, Longbo Huang, John C. S. Lui
Abstract	The web link selection problem is to select a small subset of web links from a large web link pool, and to place the selected links on a web page that can only accommodate a limited number of links, e.g., advertisements, recommendations, or news feeds. Despite the long concerned click-through rate which reflects the attractiveness of the link itself, the revenue can only be obtained from user actions after clicks, e.g., purchasing after being directed to the product pages by recommendation links. Thus, the web links have an intrinsic \emph{multi-level feedback structure}. With this observation, we consider the context-free web link selection problem, where the objective is to maximize revenue while ensuring that the attractiveness is no less than a preset threshold. The key challenge of the problem is that each link’s multi-level feedbacks are stochastic, and unobservable unless the link is selected. We model this problem with a constrained stochastic multi-armed bandit formulation, and design an efficient link selection algorithm, called Constrained Upper Confidence Bound algorithm (\textbf{Con-UCB}), and prove $O(\sqrt{T\ln T})$ bounds on both the regret and the violation of the attractiveness constraint. We conduct extensive experiments on three real-world datasets, and show that \textbf{Con-UCB} outperforms state-of-the-art context-free bandit algorithms concerning the multi-level feedback structure.
Tasks
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01702v1
PDF	http://arxiv.org/pdf/1805.01702v1.pdf
PWC	https://paperswithcode.com/paper/beyond-the-click-through-rate-web-link
Repo
Framework

CPNet: A Context Preserver Convolutional Neural Network for Detecting Shadows in Single RGB Images


Title	CPNet: A Context Preserver Convolutional Neural Network for Detecting Shadows in Single RGB Images
Authors	Sorour Mohajerani, Parvaneh Saeedi
Abstract	Automatic detection of shadow regions in an image is a difficult task due to the lack of prior information about the illumination source and the dynamic of the scene objects. To address this problem, in this paper, a deep-learning based segmentation method is proposed that identifies shadow regions at the pixel-level in a single RGB image. We exploit a novel Convolutional Neural Network (CNN) architecture to identify and extract shadow features in an end-to-end manner. This network preserves learned contexts during the training and observes the entire image to detect global and local shadow patterns simultaneously. The proposed method is evaluated on two publicly available datasets of SBU and UCF. We have improved the state-of-the-art Balanced Error Rate (BER) on these datasets by 22% and 14%, respectively.
Tasks	Detecting Shadows
Published	2018-10-13
URL	http://arxiv.org/abs/1810.05778v1
PDF	http://arxiv.org/pdf/1810.05778v1.pdf
PWC	https://paperswithcode.com/paper/cpnet-a-context-preserver-convolutional
Repo
Framework

CLINIQA: A Machine Intelligence Based Clinical Question Answering System


Title	CLINIQA: A Machine Intelligence Based Clinical Question Answering System
Authors	M A H Zahid, Ankush Mittal, R. C. Joshi, G. Atluri
Abstract	The recent developments in the field of biomedicine have made large volumes of biomedical literature available to the medical practitioners. Due to the large size and lack of efficient searching strategies, medical practitioners struggle to obtain necessary information available in the biomedical literature. Moreover, the most sophisticated search engines of age are not intelligent enough to interpret the clinicians’ questions. These facts reflect the urgent need of an information retrieval system that accepts the queries from medical practitioners’ in natural language and returns the answers quickly and efficiently. In this paper, we present an implementation of a machine intelligence based CLINIcal Question Answering system (CLINIQA) to answer medical practitioner’s questions. The system was rigorously evaluated on different text mining algorithms and the best components for the system were selected. The system makes use of Unified Medical Language System for semantic analysis of both questions and medical documents. In addition, the system employs supervised machine learning algorithms for classification of the documents, identifying the focus of the question and answer selection. Effective domain-specific heuristics are designed for answer ranking. The performance evaluation on hundred clinical questions shows the effectiveness of our approach.
Tasks	Answer Selection, Information Retrieval, Question Answering
Published	2018-05-15
URL	http://arxiv.org/abs/1805.05927v1
PDF	http://arxiv.org/pdf/1805.05927v1.pdf
PWC	https://paperswithcode.com/paper/cliniqa-a-machine-intelligence-based-clinical
Repo
Framework