October 16, 2019

3058 words 15 mins read

Paper Group ANR 978

Verisimilar Percept Sequences Tests for Autonomous Driving Intelligent Agent Assessment. Local Homology of Word Embeddings. Mining Entity Synonyms with Efficient Neural Set Generation. Seuillage par hystérésis pour le test de photo-consistance des voxels dans le cadre de la reconstruction 3D. Conservative Exploration using Interleaving. Light-weigh …

Verisimilar Percept Sequences Tests for Autonomous Driving Intelligent Agent Assessment


Title	Verisimilar Percept Sequences Tests for Autonomous Driving Intelligent Agent Assessment
Authors	Thomio Watanabe, Denis Wolf
Abstract	The autonomous car technology promises to replace human drivers with safer driving systems. But although autonomous cars can become safer than human drivers this is a long process that is going to be refined over time. Before these vehicles are deployed on urban roads a minimum safety level must be assured. Since the autonomous car technology is still under development there is no standard methodology to evaluate such systems. It is important to completely understand the technology that is being developed to design efficient means to evaluate it. In this paper we assume safety-critical systems reliability as a safety measure. We model an autonomous road vehicle as an intelligent agent and we approach its evaluation from an artificial intelligence perspective. Our focus is the evaluation of perception and decision making systems and also to propose a systematic method to evaluate their integration in the vehicle. We identify critical aspects of the data dependency from the artificial intelligence state of the art models and we also propose procedures to reproduce them.
Tasks	Autonomous Driving, Decision Making
Published	2018-05-07
URL	http://arxiv.org/abs/1805.02754v1
PDF	http://arxiv.org/pdf/1805.02754v1.pdf
PWC	https://paperswithcode.com/paper/verisimilar-percept-sequences-tests-for
Repo
Framework

Local Homology of Word Embeddings


Title	Local Homology of Word Embeddings
Authors	Tadas Temčinas
Abstract	Topological data analysis (TDA) has been widely used to make progress on a number of problems. However, it seems that TDA application in natural language processing (NLP) is at its infancy. In this paper we try to bridge the gap by arguing why TDA tools are a natural choice when it comes to analysing word embedding data. We describe a parallelisable unsupervised learning algorithm based on local homology of datapoints and show some experimental results on word embedding data. We see that local homology of datapoints in word embedding data contains some information that can potentially be used to solve the word sense disambiguation problem.
Tasks	Topological Data Analysis, Word Embeddings, Word Sense Disambiguation
Published	2018-10-24
URL	http://arxiv.org/abs/1810.10136v1
PDF	http://arxiv.org/pdf/1810.10136v1.pdf
PWC	https://paperswithcode.com/paper/local-homology-of-word-embeddings
Repo
Framework

Mining Entity Synonyms with Efficient Neural Set Generation


Title	Mining Entity Synonyms with Efficient Neural Set Generation
Authors	Jiaming Shen, Ruiliang Lyu, Xiang Ren, Michelle Vanni, Brian Sadler, Jiawei Han
Abstract	Mining entity synonym sets (i.e., sets of terms referring to the same entity) is an important task for many entity-leveraging applications. Previous work either rank terms based on their similarity to a given query term, or treats the problem as a two-phase task (i.e., detecting synonymy pairs, followed by organizing these pairs into synonym sets). However, these approaches fail to model the holistic semantics of a set and suffer from the error propagation issue. Here we propose a new framework, named SynSetMine, that efficiently generates entity synonym sets from a given vocabulary, using example sets from external knowledge bases as distant supervision. SynSetMine consists of two novel modules: (1) a set-instance classifier that jointly learns how to represent a permutation invariant synonym set and whether to include a new instance (i.e., a term) into the set, and (2) a set generation algorithm that enumerates the vocabulary only once and applies the learned set-instance classifier to detect all entity synonym sets in it. Experiments on three real datasets from different domains demonstrate both effectiveness and efficiency of SynSetMine for mining entity synonym sets.
Tasks
Published	2018-11-16
URL	http://arxiv.org/abs/1811.07032v1
PDF	http://arxiv.org/pdf/1811.07032v1.pdf
PWC	https://paperswithcode.com/paper/mining-entity-synonyms-with-efficient-neural
Repo
Framework

Seuillage par hystérésis pour le test de photo-consistance des voxels dans le cadre de la reconstruction 3D


Title	Seuillage par hystérésis pour le test de photo-consistance des voxels dans le cadre de la reconstruction 3D
Authors	Mohamed Chafik Bakkay, Walid Barhoumi, Ezzeddine Zagrouba
Abstract	Voxel coloring is a popular method of reconstructing a three-dimensional surface model from a set of calibrated 2D images. However, the reconstruction quality is largely dependent on a thresholding procedure allowing the authors to decide, for each voxel, whether it is photo-consistent or not. Even so, this method is widely used because of its simplicity and low computational cost. We have returned to this method in order to propose an improvement in the thresholding step which will be fully automated. Indeed, the geometrical information is implicitly integrated using an hysteresis thresholding which takes into account the spatial coherence of color voxels. Moreover, the ambiguity of choosing the thresholds is extremely minimized by defining a fuzzy degree of membership of each voxel into the class of consistent voxels. Also, there is no need for preset thresholds since the hysteresis ones are defined automatically and adaptively depending on the number of images that the voxel isprojected onto. Preliminary results are very promising and demonstrate that the proposed method performs automatically precise and smooth volumetric scene reconstruction.
Tasks
Published	2018-09-17
URL	http://arxiv.org/abs/1809.06070v1
PDF	http://arxiv.org/pdf/1809.06070v1.pdf
PWC	https://paperswithcode.com/paper/seuillage-par-hysteresis-pour-le-test-de
Repo
Framework

Conservative Exploration using Interleaving


Title	Conservative Exploration using Interleaving
Authors	Sumeet Katariya, Branislav Kveton, Zheng Wen, Vamsi K. Potluru
Abstract	In many practical problems, a learning agent may want to learn the best action in hindsight without ever taking a bad action, which is significantly worse than the default production action. In general, this is impossible because the agent has to explore unknown actions, some of which can be bad, to learn better actions. However, when the actions are combinatorial, this may be possible if the unknown action can be evaluated by interleaving it with the production action. We formalize this concept as learning in stochastic combinatorial semi-bandits with exchangeable actions. We design efficient learning algorithms for this problem, bound their n-step regret, and evaluate them on both synthetic and real-world problems. Our real-world experiments show that our algorithms can learn to recommend K most attractive movies without ever violating a strict production constraint, both overall and subject to a diversity constraint.
Tasks
Published	2018-06-03
URL	http://arxiv.org/abs/1806.00892v1
PDF	http://arxiv.org/pdf/1806.00892v1.pdf
PWC	https://paperswithcode.com/paper/conservative-exploration-using-interleaving
Repo
Framework

Light-weight Head Pose Invariant Gaze Tracking


Title	Light-weight Head Pose Invariant Gaze Tracking
Authors	Rajeev Ranjan, Shalini De Mello, Jan Kautz
Abstract	Unconstrained remote gaze tracking using off-the-shelf cameras is a challenging problem. Recently, promising algorithms for appearance-based gaze estimation using convolutional neural networks (CNN) have been proposed. Improving their robustness to various confounding factors including variable head pose, subject identity, illumination and image quality remain open problems. In this work, we study the effect of variable head pose on machine learning regressors trained to estimate gaze direction. We propose a novel branched CNN architecture that improves the robustness of gaze classifiers to variable head pose, without increasing computational cost. We also present various procedures to effectively train our gaze network including transfer learning from the more closely related task of object viewpoint estimation and from a large high-fidelity synthetic gaze dataset, which enable our ten times faster gaze network to achieve competitive accuracy to its current state-of-the-art direct competitor.
Tasks	Gaze Estimation, Transfer Learning, Viewpoint Estimation
Published	2018-04-23
URL	http://arxiv.org/abs/1804.08572v1
PDF	http://arxiv.org/pdf/1804.08572v1.pdf
PWC	https://paperswithcode.com/paper/light-weight-head-pose-invariant-gaze
Repo
Framework

Persistent Monitoring of Stochastic Spatio-temporal Phenomena with a Small Team of Robots


Title	Persistent Monitoring of Stochastic Spatio-temporal Phenomena with a Small Team of Robots
Authors	Sahil Garg, Nora Ayanian
Abstract	This paper presents a solution for persistent monitoring of real-world stochastic phenomena, where the underlying covariance structure changes sharply across time, using a small number of mobile robot sensors. We propose an adaptive solution for the problem where stochastic real-world dynamics are modeled as a Gaussian Process (GP). The belief on the underlying covariance structure is learned from recently observed dynamics as a Gaussian Mixture (GM) in the low-dimensional hyper-parameters space of the GP and adapted across time using Sequential Monte Carlo methods. Each robot samples a belief point from the GM and locally optimizes a set of informative regions by greedy maximization of the submodular entropy function. The key contributions of this paper are threefold: adapting the belief on the covariance using Markov Chain Monte Carlo (MCMC) sampling such that particles survive even under sharp covariance changes across time; exploiting the belief to transform the problem of entropy maximization into a decentralized one; and developing an approximation algorithm to maximize entropy on a set of informative regions in the continuous space. We illustrate the application of the proposed solution through extensive simulations using an artificial dataset and multiple real datasets from fixed sensor deployments, and compare it to three competing state-of-the-art approaches.
Tasks
Published	2018-04-27
URL	http://arxiv.org/abs/1804.10544v1
PDF	http://arxiv.org/pdf/1804.10544v1.pdf
PWC	https://paperswithcode.com/paper/persistent-monitoring-of-stochastic-spatio
Repo
Framework

NumtaDB - Assembled Bengali Handwritten Digits


Title	NumtaDB - Assembled Bengali Handwritten Digits
Authors	Samiul Alam, Tahsin Reasat, Rashed Mohammad Doha, Ahmed Imtiaz Humayun
Abstract	To benchmark Bengali digit recognition algorithms, a large publicly available dataset is required which is free from biases originating from geographical location, gender, and age. With this aim in mind, NumtaDB, a dataset consisting of more than 85,000 images of hand-written Bengali digits, has been assembled. This paper documents the collection and curation process of numerals along with the salient statistics of the dataset.
Tasks
Published	2018-06-06
URL	http://arxiv.org/abs/1806.02452v1
PDF	http://arxiv.org/pdf/1806.02452v1.pdf
PWC	https://paperswithcode.com/paper/numtadb-assembled-bengali-handwritten-digits
Repo
Framework

Sentiment Analysis on Speaker Specific Speech Data


Title	Sentiment Analysis on Speaker Specific Speech Data
Authors	Maghilnan S, Rajesh Kumar M
Abstract	Sentiment analysis has evolved over past few decades, most of the work in it revolved around textual sentiment analysis with text mining techniques. But audio sentiment analysis is still in a nascent stage in the research community. In this proposed research, we perform sentiment analysis on speaker discriminated speech transcripts to detect the emotions of the individual speakers involved in the conversation. We analyzed different techniques to perform speaker discrimination and sentiment analysis to find efficient algorithms to perform this task.
Tasks	Sentiment Analysis
Published	2018-02-17
URL	http://arxiv.org/abs/1802.06209v1
PDF	http://arxiv.org/pdf/1802.06209v1.pdf
PWC	https://paperswithcode.com/paper/sentiment-analysis-on-speaker-specific-speech
Repo
Framework

Wavelet based edge feature enhancement for convolutional neural networks


Title	Wavelet based edge feature enhancement for convolutional neural networks
Authors	D. D. N. De Silva, S. Fernando, I. T. S. Piyatilake, A. V. S. Karunarathne
Abstract	Convolutional neural networks are able to perform a hierarchical learning process starting with local features. However, a limited attention is paid to enhancing such elementary level features like edges. We propose and evaluate two wavelet-based edge feature enhancement methods to preprocess the input images to convolutional neural networks. The first method develops feature enhanced representations by decomposing the input images using wavelet transform and limited reconstructing subsequently. The second method develops such feature enhanced inputs to the network using local modulus maxima of wavelet coefficients. For each method, we have developed a new preprocessing layer by implementing each purposed method and have appended to the network architecture. Our empirical evaluations demonstrate that the proposed methods are outperforming the baselines and previously published work with significant accuracy gains.
Tasks
Published	2018-08-29
URL	http://arxiv.org/abs/1809.00982v2
PDF	http://arxiv.org/pdf/1809.00982v2.pdf
PWC	https://paperswithcode.com/paper/wavelet-based-edge-feature-enhancement-for
Repo
Framework

Automated identification of hookahs (waterpipes) on Instagram: an application in feature extraction using Convolutional Neural Network and Support Vector Machine classification


Title	Automated identification of hookahs (waterpipes) on Instagram: an application in feature extraction using Convolutional Neural Network and Support Vector Machine classification
Authors	Youshan Zhang, Jon-Patrick Allem, Jennifer B. Unger, Tess Boley Cruz
Abstract	Background: Instagram, with millions of posts per day, can be used to inform public health surveillance targets and policies. However, current research relying on image-based data often relies on hand coding of images which is time consuming and costly, ultimately limiting the scope of the study. Current best practices in automated image classification (e.g., support vector machine (SVM), Backpropagation (BP) neural network, and artificial neural network) are limited in their capacity to accurately distinguish between objects within images. Objective: This study demonstrates how convolutional neural network (CNN) can be used to extract unique features within an image and how SVM can then be used to classify the image. Methods: Images of waterpipes or hookah (an emerging tobacco product possessing similar harms to that of cigarettes) were collected from Instagram and used in analyses (n=840). CNN was used to extract unique features from images identified to contain waterpipes. A SVM classifier was built to distinguish between images with and without waterpipes. Methods for image classification were then compared to show how a CNN + SVM classifier could improve accuracy. Results: As the number of the validated training images increased, the total number of extracted features increased. Additionally, as the number of features learned by the SVM classifier increased, the average level of accuracy increased. Overall, 99.5% of the 420 images classified were correctly identified as either hookah or non-hookah images. This level of accuracy was an improvement over earlier methods that used SVM, CNN or Bag of Features (BOF) alone. Conclusions: CNN extracts more features of the images allowing a SVM classifier to be better informed, resulting in higher accuracy compared with methods that extract fewer features. Future research can use this method to grow the scope of image-based studies.
Tasks	Image Classification
Published	2018-10-21
URL	http://arxiv.org/abs/1810.08881v1
PDF	http://arxiv.org/pdf/1810.08881v1.pdf
PWC	https://paperswithcode.com/paper/automated-identification-of-hookahs
Repo
Framework

Fully-Convolutional Point Networks for Large-Scale Point Clouds


Title	Fully-Convolutional Point Networks for Large-Scale Point Clouds
Authors	Dario Rethage, Johanna Wald, Jürgen Sturm, Nassir Navab, Federico Tombari
Abstract	This work proposes a general-purpose, fully-convolutional network architecture for efficiently processing large-scale 3D data. One striking characteristic of our approach is its ability to process unorganized 3D representations such as point clouds as input, then transforming them internally to ordered structures to be processed via 3D convolutions. In contrast to conventional approaches that maintain either unorganized or organized representations, from input to output, our approach has the advantage of operating on memory efficient input data representations while at the same time exploiting the natural structure of convolutional operations to avoid the redundant computing and storing of spatial information in the network. The network eliminates the need to pre- or post process the raw sensor data. This, together with the fully-convolutional nature of the network, makes it an end-to-end method able to process point clouds of huge spaces or even entire rooms with up to 200k points at once. Another advantage is that our network can produce either an ordered output or map predictions directly onto the input cloud, thus making it suitable as a general-purpose point cloud descriptor applicable to many 3D tasks. We demonstrate our network’s ability to effectively learn both low-level features as well as complex compositional relationships by evaluating it on benchmark datasets for semantic voxel segmentation, semantic part segmentation and 3D scene captioning.
Tasks	Semantic Segmentation
Published	2018-08-21
URL	http://arxiv.org/abs/1808.06840v1
PDF	http://arxiv.org/pdf/1808.06840v1.pdf
PWC	https://paperswithcode.com/paper/fully-convolutional-point-networks-for-large
Repo
Framework

A Fast Anderson-Chebyshev Acceleration for Nonlinear Optimization


Title	A Fast Anderson-Chebyshev Acceleration for Nonlinear Optimization
Authors	Zhize Li, Jian Li
Abstract	Anderson acceleration (or Anderson mixing) is an efficient acceleration method for fixed point iterations $x_{t+1}=G(x_t)$, e.g., gradient descent can be viewed as iteratively applying the operation $G(x) \triangleq x-\alpha\nabla f(x)$. It is known that Anderson acceleration is quite efficient in practice and can be viewed as an extension of Krylov subspace methods for nonlinear problems. In this paper, we show that Anderson acceleration with Chebyshev polynomial can achieve the optimal convergence rate $O(\sqrt{\kappa}\ln\frac{1}{\epsilon})$, which improves the previous result $O(\kappa\ln\frac{1}{\epsilon})$ provided by (Toth and Kelley, 2015) for quadratic functions. Moreover, we provide a convergence analysis for minimizing general nonlinear problems. Besides, if the hyperparameters (e.g., the Lipschitz smooth parameter $L$) are not available, we propose a guessing algorithm for guessing them dynamically and also prove a similar convergence rate. Finally, the experimental results demonstrate that the proposed Anderson-Chebyshev acceleration method converges significantly faster than other algorithms, e.g., vanilla gradient descent (GD), Nesterov’s Accelerated GD. Also, these algorithms combined with the proposed guessing algorithm (guessing the hyperparameters dynamically) achieve much better performance.
Tasks
Published	2018-09-07
URL	https://arxiv.org/abs/1809.02341v4
PDF	https://arxiv.org/pdf/1809.02341v4.pdf
PWC	https://paperswithcode.com/paper/an-anderson-chebyshev-mixing-method-for
Repo
Framework

Scalable Sparse Subspace Clustering via Ordered Weighted $\ell_1$ Regression


Title	Scalable Sparse Subspace Clustering via Ordered Weighted $\ell_1$ Regression
Authors	Urvashi Oswal, Robert Nowak
Abstract	The main contribution of the paper is a new approach to subspace clustering that is significantly more computationally efficient and scalable than existing state-of-the-art methods. The central idea is to modify the regression technique in sparse subspace clustering (SSC) by replacing the $\ell_1$ minimization with a generalization called Ordered Weighted $\ell_1$ (OWL) minimization which performs simultaneous regression and clustering of correlated variables. Using random geometric graph theory, we prove that OWL regression selects more points within each subspace, resulting in better clustering results. This allows for accurate subspace clustering based on regression solutions for only a small subset of the total dataset, significantly reducing the computational complexity compared to SSC. In experiments, we find that our OWL approach can achieve a speedup of 20$\times$ to 30$\times$ for synthetic problems and 4$\times$ to 8$\times$ on real data problems.
Tasks
Published	2018-07-10
URL	http://arxiv.org/abs/1807.03746v1
PDF	http://arxiv.org/pdf/1807.03746v1.pdf
PWC	https://paperswithcode.com/paper/scalable-sparse-subspace-clustering-via
Repo
Framework

Attentional Heterogeneous Graph Neural Network: Application to Program Reidentification


Title	Attentional Heterogeneous Graph Neural Network: Application to Program Reidentification
Authors	Shen Wang, Zhengzhang Chen, Ding Li, Lu-An Tang, Jingchao Ni, Zhichun Li, Junghwan Rhee, Haifeng Chen, Philip S. Yu
Abstract	Program or process is an integral part of almost every IT/OT system. Can we trust the identity/ID (e.g., executable name) of the program? To avoid detection, malware may disguise itself using the ID of a legitimate program, and a system tool (e.g., PowerShell) used by the attackers may have the fake ID of another common software, which is less sensitive. However, existing intrusion detection techniques often overlook this critical program reidentification problem (i.e., checking the program’s identity). In this paper, we propose an attentional heterogeneous graph neural network model (DeepHGNN) to verify the program’s identity based on its system behaviors. The key idea is to leverage the representation learning of the heterogeneous program behavior graph to guide the reidentification process. We formulate the program reidentification as a graph classification problem and develop an effective attentional heterogeneous graph embedding algorithm to solve it. Extensive experiments — using real-world enterprise monitoring data and real attacks — demonstrate the effectiveness of DeepHGNN across multiple popular metrics and the robustness to the normal dynamic changes like program version upgrades.
Tasks	Graph Classification, Graph Embedding, Intrusion Detection, Representation Learning
Published	2018-12-10
URL	https://arxiv.org/abs/1812.04064v2
PDF	https://arxiv.org/pdf/1812.04064v2.pdf
PWC	https://paperswithcode.com/paper/deep-program-reidentification-a-graph-neural
Repo
Framework