July 28, 2019

3071 words 15 mins read

Paper Group ANR 291

Reasoning About Liquids via Closed-Loop Simulation. Coalition formation for Multi-agent Pursuit based on Neural Network and AGRMF Model. Adversarial Source Identification Game with Corrupted Training. Three-Stream Convolutional Networks for Video-based Person Re-Identification. Layer-wise training of deep networks using kernel similarity. Context A …

Reasoning About Liquids via Closed-Loop Simulation


Title	Reasoning About Liquids via Closed-Loop Simulation
Authors	Connor Schenck, Dieter Fox
Abstract	Simulators are powerful tools for reasoning about a robot’s interactions with its environment. However, when simulations diverge from reality, that reasoning becomes less useful. In this paper, we show how to close the loop between liquid simulation and real-time perception. We use observations of liquids to correct errors when tracking the liquid’s state in a simulator. Our results show that closed-loop simulation is an effective way to prevent large divergence between the simulated and real liquid states. As a direct consequence of this, our method can enable reasoning about liquids that would otherwise be infeasible due to large divergences, such as reasoning about occluded liquid.
Tasks
Published	2017-03-05
URL	http://arxiv.org/abs/1703.01656v2
PDF	http://arxiv.org/pdf/1703.01656v2.pdf
PWC	https://paperswithcode.com/paper/reasoning-about-liquids-via-closed-loop
Repo
Framework

Coalition formation for Multi-agent Pursuit based on Neural Network and AGRMF Model


Title	Coalition formation for Multi-agent Pursuit based on Neural Network and AGRMF Model
Authors	Zhaoyi Pei, Songhao Piao, Mohammed Ei Souidi
Abstract	An approach for coalition formation of multi-agent pursuit based on neural network and AGRMF model is proposed.This paper constructs a novel neural work called AGRMF-ANN which consists of feature extraction part and group generation part. On one hand,The convolutional layers of feature extraction part can abstract the features of agent group role membership function(AGRMF) for all of the groups,on the other hand,those features will be fed to the group generation part based on self-organizing map(SOM) layer which is used to group the pursuers with similar features in the same group. Besides, we also come up the group attractiveness function(GAF) to evaluate the quality of groups and the pursuers contribution in order to adjust the main ability indicators of AGRMF and other weight of all neural network. The simulation experiment showed that this proposal can improve the effectiveness of coalition formation for multi-agent pursuit and ability to adopt pursuit-evasion problem with the scale of pursuer team growing.
Tasks
Published	2017-07-17
URL	http://arxiv.org/abs/1707.05001v1
PDF	http://arxiv.org/pdf/1707.05001v1.pdf
PWC	https://paperswithcode.com/paper/coalition-formation-for-multi-agent-pursuit
Repo
Framework

Adversarial Source Identification Game with Corrupted Training


Title	Adversarial Source Identification Game with Corrupted Training
Authors	Mauro Barni, Benedetta Tondi
Abstract	We study a variant of the source identification game with training data in which part of the training data is corrupted by an attacker. In the addressed scenario, the defender aims at deciding whether a test sequence has been drawn according to a discrete memoryless source $X \sim P_X$, whose statistics are known to him through the observation of a training sequence generated by $X$. In order to undermine the correct decision under the alternative hypothesis that the test sequence has not been drawn from $X$, the attacker can modify a sequence produced by a source $Y \sim P_Y$ up to a certain distortion, and corrupt the training sequence either by adding some fake samples or by replacing some samples with fake ones. We derive the unique rationalizable equilibrium of the two versions of the game in the asymptotic regime and by assuming that the defender bases its decision by relying only on the first order statistics of the test and the training sequences. By mimicking Stein’s lemma, we derive the best achievable performance for the defender when the first type error probability is required to tend to zero exponentially fast with an arbitrarily small, yet positive, error exponent. We then use such a result to analyze the ultimate distinguishability of any two sources as a function of the allowed distortion and the fraction of corrupted samples injected into the training sequence.
Tasks
Published	2017-03-27
URL	http://arxiv.org/abs/1703.09244v1
PDF	http://arxiv.org/pdf/1703.09244v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-source-identification-game-with
Repo
Framework

Three-Stream Convolutional Networks for Video-based Person Re-Identification


Title	Three-Stream Convolutional Networks for Video-based Person Re-Identification
Authors	Zeng Yu, Tianrui Li, Ning Yu, Xun Gong, Ke Chen, Yi Pan
Abstract	This paper aims to develop a new architecture that can make full use of the feature maps of convolutional networks. To this end, we study a number of methods for video-based person re-identification and make the following findings: 1) Max-pooling only focuses on the maximum value of a receptive field, wasting a lot of information. 2) Networks with different streams even including the one with the worst performance work better than networks with same streams, where each one has the best performance alone. 3) A full connection layer at the end of convolutional networks is not necessary. Based on these studies, we propose a new convolutional architecture termed Three-Stream Convolutional Networks (TSCN). It first uses different streams to learn different aspects of feature maps for attentive spatio-temporal fusion of video, and then merges them together to study some union features. To further utilize the feature maps, two architectures are designed by using the strategies of multi-scale and upsampling. Comparative experiments on iLIDS-VID, PRID-2011 and MARS datasets illustrate that the proposed architectures are significantly better for feature extraction than the state-of-the-art models.
Tasks	Person Re-Identification, Video-Based Person Re-Identification
Published	2017-11-22
URL	http://arxiv.org/abs/1712.01652v1
PDF	http://arxiv.org/pdf/1712.01652v1.pdf
PWC	https://paperswithcode.com/paper/three-stream-convolutional-networks-for-video
Repo
Framework

Layer-wise training of deep networks using kernel similarity


Title	Layer-wise training of deep networks using kernel similarity
Authors	Mandar Kulkarni, Shirish Karande
Abstract	Deep learning has shown promising results in many machine learning applications. The hierarchical feature representation built by deep networks enable compact and precise encoding of the data. A kernel analysis of the trained deep networks demonstrated that with deeper layers, more simple and more accurate data representations are obtained. In this paper, we propose an approach for layer-wise training of a deep network for the supervised classification task. A transformation matrix of each layer is obtained by solving an optimization aimed at a better representation where a subsequent layer builds its representation on the top of the features produced by a previous layer. We compared the performance of our approach with a DNN trained using back-propagation which has same architecture as ours. Experimental results on the real image datasets demonstrate efficacy of our approach. We also performed kernel analysis of layer representations to validate the claim of better feature encoding.
Tasks
Published	2017-03-21
URL	http://arxiv.org/abs/1703.07115v1
PDF	http://arxiv.org/pdf/1703.07115v1.pdf
PWC	https://paperswithcode.com/paper/layer-wise-training-of-deep-networks-using
Repo
Framework

Context Augmentation for Convolutional Neural Networks


Title	Context Augmentation for Convolutional Neural Networks
Authors	Aysegul Dundar, Ignacio Garcia-Dorado
Abstract	Recent enhancements of deep convolutional neural networks (ConvNets) empowered by enormous amounts of labeled data have closed the gap with human performance for many object recognition tasks. These impressive results have generated interest in understanding and visualization of ConvNets. In this work, we study the effect of background in the task of image classification. Our results show that changing the backgrounds of the training datasets can have drastic effects on testing accuracies. Furthermore, we enhance existing augmentation techniques with the foreground segmented objects. The findings of this work are important in increasing the accuracies when only a small dataset is available, in creating datasets, and creating synthetic images.
Tasks	Image Classification, Object Recognition
Published	2017-11-22
URL	http://arxiv.org/abs/1712.01653v2
PDF	http://arxiv.org/pdf/1712.01653v2.pdf
PWC	https://paperswithcode.com/paper/context-augmentation-for-convolutional-neural
Repo
Framework

Novel Evaluation Metrics for Seam Carving based Image Retargeting


Title	Novel Evaluation Metrics for Seam Carving based Image Retargeting
Authors	Tam V. Nguyen, Guangyu Gao
Abstract	Image retargeting effectively resizes images by preserving the recognizability of important image regions. Most of retargeting methods rely on good importance maps as a cue to retain or remove certain regions in the input image. In addition, the traditional evaluation exhaustively depends on user ratings. There is a legitimate need for a methodological approach for evaluating retargeted results. Therefore, in this paper, we conduct a study and analysis on the prominent method in image retargeting, Seam Carving. First, we introduce two novel evaluation metrics which can be considered as the proxy of user ratings. Second, we exploit salient object dataset as a benchmark for this task. We then investigate different types of importance maps for this particular problem. The experiments show that humans in general agree with the evaluation metrics on the retargeted results and some importance map methods are consistently more favorable than others.
Tasks
Published	2017-09-22
URL	http://arxiv.org/abs/1709.07565v1
PDF	http://arxiv.org/pdf/1709.07565v1.pdf
PWC	https://paperswithcode.com/paper/novel-evaluation-metrics-for-seam-carving
Repo
Framework

A new belief Markov chain model and its application in inventory prediction


Title	A new belief Markov chain model and its application in inventory prediction
Authors	Zichang He, Wen Jiang
Abstract	Markov chain model is widely applied in many fields, especially the field of prediction. The classical Discrete-time Markov chain(DTMC) is a widely used method for prediction. However, the classical DTMC model has some limitation when the system is complex with uncertain information or state space is not discrete. To address it, a new belief Markov chain model is proposed by combining Dempster-Shafer evidence theory with Markov chain. In our model, the uncertain data is allowed to be handle in the form of interval number and the basic probability assignment(BPA) is generated based on the distance between interval numbers. The new belief Markov chain model overcomes the shortcomings of classical Markov chain and has an efficient ability in dealing with uncertain information. Moreover, an example of inventory prediction and the comparison between our model and classical DTMC model can show the effectiveness and rationality of our proposed model.
Tasks
Published	2017-03-06
URL	http://arxiv.org/abs/1703.01963v1
PDF	http://arxiv.org/pdf/1703.01963v1.pdf
PWC	https://paperswithcode.com/paper/a-new-belief-markov-chain-model-and-its
Repo
Framework

Classification of COPD with Multiple Instance Learning


Title	Classification of COPD with Multiple Instance Learning
Authors	Veronika Cheplygina, Lauge Sørensen, David M. J. Tax, Jesper Holst Pedersen, Marco Loog, Marleen de Bruijne
Abstract	Chronic obstructive pulmonary disease (COPD) is a lung disease where early detection benefits the survival rate. COPD can be quantified by classifying patches of computed tomography images, and combining patch labels into an overall diagnosis for the image. As labeled patches are often not available, image labels are propagated to the patches, incorrectly labeling healthy patches in COPD patients as being affected by the disease. We approach quantification of COPD from lung images as a multiple instance learning (MIL) problem, which is more suitable for such weakly labeled data. We investigate various MIL assumptions in the context of COPD and show that although a concept region with COPD-related disease patterns is present, considering the whole distribution of lung tissue patches improves the performance. The best method is based on averaging instances and obtains an AUC of 0.742, which is higher than the previously reported best of 0.713 on the same dataset. Using the full training set further increases performance to 0.776, which is significantly higher (DeLong test) than previous results.
Tasks	Multiple Instance Learning
Published	2017-03-15
URL	http://arxiv.org/abs/1703.04980v1
PDF	http://arxiv.org/pdf/1703.04980v1.pdf
PWC	https://paperswithcode.com/paper/classification-of-copd-with-multiple-instance
Repo
Framework

Multi-Label Classification of Patient Notes a Case Study on ICD Code Assignment


Title	Multi-Label Classification of Patient Notes a Case Study on ICD Code Assignment
Authors	Tal Baumel, Jumana Nassour-Kassis, Raphael Cohen, Michael Elhadad, No`emie Elhadad \|
Abstract	In the context of the Electronic Health Record, automated diagnosis coding of patient notes is a useful task, but a challenging one due to the large number of codes and the length of patient notes. We investigate four models for assigning multiple ICD codes to discharge summaries taken from both MIMIC II and III. We present Hierarchical Attention-GRU (HA-GRU), a hierarchical approach to tag a document by identifying the sentences relevant for each label. HA-GRU achieves state-of-the art results. Furthermore, the learned sentence-level attention layer highlights the model decision process, allows easier error analysis, and suggests future directions for improvement.
Tasks	Multi-Label Classification
Published	2017-09-27
URL	http://arxiv.org/abs/1709.09587v3
PDF	http://arxiv.org/pdf/1709.09587v3.pdf
PWC	https://paperswithcode.com/paper/multi-label-classification-of-patient-notes-a
Repo
Framework

VOIDD: automatic vessel of intervention dynamic detection in PCI procedures


Title	VOIDD: automatic vessel of intervention dynamic detection in PCI procedures
Authors	Ketan Bacchuwar, Jean Cousty, Régis Vaillant, Laurent Najman
Abstract	In this article, we present the work towards improving the overall workflow of the Percutaneous Coronary Interventions (PCI) procedures by capacitating the imaging instruments to precisely monitor the steps of the procedure. In the long term, such capabilities can be used to optimize the image acquisition to reduce the amount of dose or contrast media employed during the procedure. We present the automatic VOIDD algorithm to detect the vessel of intervention which is going to be treated during the procedure by combining information from the vessel image with contrast agent injection and images acquired during guidewire tip navigation. Due to the robust guidewire tip segmentation method, this algorithm is also able to automatically detect the sequence corresponding to guidewire navigation. We present an evaluation methodology which characterizes the correctness of the guide wire tip detection and correct identification of the vessel navigated during the procedure. On a dataset of 2213 images from 8 sequences of 4 patients, VOIDD identifies vessel-of-intervention with accuracy in the range of 88% or above and absence of tip with accuracy in range of 98% or above depending on the test case.
Tasks
Published	2017-10-12
URL	http://arxiv.org/abs/1710.04476v1
PDF	http://arxiv.org/pdf/1710.04476v1.pdf
PWC	https://paperswithcode.com/paper/voidd-automatic-vessel-of-intervention
Repo
Framework

Graphical Lasso and Thresholding: Equivalence and Closed-form Solutions


Title	Graphical Lasso and Thresholding: Equivalence and Closed-form Solutions
Authors	Salar Fattahi, Somayeh Sojoudi
Abstract	Graphical Lasso (GL) is a popular method for learning the structure of an undirected graphical model, which is based on an $l_1$ regularization technique. The objective of this paper is to compare the computationally-heavy GL technique with a numerically-cheap heuristic method that is based on simply thresholding the sample covariance matrix. To this end, two notions of sign-consistent and inverse-consistent matrices are developed, and then it is shown that the thresholding and GL methods are equivalent if: (i) the thresholded sample covariance matrix is both sign-consistent and inverse-consistent, and (ii) the gap between the largest thresholded and the smallest un-thresholded entries of the sample covariance matrix is not too small. By building upon this result, it is proved that the GL method—as a conic optimization problem—has an explicit closed-form solution if the thresholded sample covariance matrix has an acyclic structure. This result is then generalized to arbitrary sparse support graphs, where a formula is found to obtain an approximate solution of GL. Furthermore, it is shown that the approximation error of the derived explicit formula decreases exponentially fast with respect to the length of the minimum-length cycle of the sparsity graph. The developed results are demonstrated on synthetic data, functional MRI data, traffic flows for transportation networks, and massive randomly generated data sets. We show that the proposed method can obtain an accurate approximation of the GL for instances with the sizes as large as $80,000\times 80,000$ (more than 3.2 billion variables) in less than 30 minutes on a standard laptop computer running MATLAB, while other state-of-the-art methods do not converge within 4 hours.
Tasks
Published	2017-08-30
URL	https://arxiv.org/abs/1708.09479v3
PDF	https://arxiv.org/pdf/1708.09479v3.pdf
PWC	https://paperswithcode.com/paper/graphical-lasso-and-thresholding-equivalence
Repo
Framework

Bangla Word Clustering Based on Tri-gram, 4-gram and 5-gram Language Model


Title	Bangla Word Clustering Based on Tri-gram, 4-gram and 5-gram Language Model
Authors	Dipaloke Saha, Md Saddam Hossain, MD. Saiful Islam, Sabir Ismail
Abstract	In this paper, we describe a research method that generates Bangla word clusters on the basis of relating to meaning in language and contextual similarity. The importance of word clustering is in parts of speech (POS) tagging, word sense disambiguation, text classification, recommender system, spell checker, grammar checker, knowledge discover and for many others Natural Language Processing (NLP) applications. In the history of word clustering, English and some other languages have already implemented some methods on word clustering efficiently. But due to lack of the resources, word clustering in Bangla has not been still implemented efficiently. Presently, its implementation is in the beginning stage. In some research of word clustering in English based on preceding and next five words of a key word they found an efficient result. Now, we are trying to implement the tri-gram, 4-gram and 5-gram model of word clustering for Bangla to observe which one is the best among them. We have started our research with quite a large corpus of approximate 1 lakh Bangla words. We are using a machine learning technique in this research. We will generate word clusters and analyze the clusters by testing some different threshold values.
Tasks	Language Modelling, Recommendation Systems, Text Classification, Word Sense Disambiguation
Published	2017-01-27
URL	http://arxiv.org/abs/1701.08702v1
PDF	http://arxiv.org/pdf/1701.08702v1.pdf
PWC	https://paperswithcode.com/paper/bangla-word-clustering-based-on-tri-gram-4
Repo
Framework

Muon Trigger for Mobile Phones


Title	Muon Trigger for Mobile Phones
Authors	Maxim Borisyak, Michail Usvyatsov, Michael Mulhearn, Chase Shimmin, Andrey Ustyuzhanin
Abstract	The CRAYFIS experiment proposes to use privately owned mobile phones as a ground detector array for Ultra High Energy Cosmic Rays. Upon interacting with Earth’s atmosphere, these events produce extensive particle showers which can be detected by cameras on mobile phones. A typical shower contains minimally-ionizing particles such as muons. As these particles interact with CMOS image sensors, they may leave tracks of faintly-activated pixels that are sometimes hard to distinguish from random detector noise. Triggers that rely on the presence of very bright pixels within an image frame are not efficient in this case. We present a trigger algorithm based on Convolutional Neural Networks which selects images containing such tracks and are evaluated in a lazy manner: the response of each successive layer is computed only if activation of the current layer satisfies a continuation criterion. Usage of neural networks increases the sensitivity considerably comparable with image thresholding, while the lazy evaluation allows for execution of the trigger under the limited computational power of mobile phones.
Tasks
Published	2017-09-25
URL	http://arxiv.org/abs/1709.08605v1
PDF	http://arxiv.org/pdf/1709.08605v1.pdf
PWC	https://paperswithcode.com/paper/muon-trigger-for-mobile-phones
Repo
Framework

Hierarchical Detail Enhancing Mesh-Based Shape Generation with 3D Generative Adversarial Network


Title	Hierarchical Detail Enhancing Mesh-Based Shape Generation with 3D Generative Adversarial Network
Authors	Chiyu “Max” Jiang, Philip Marcus
Abstract	Automatic mesh-based shape generation is of great interest across a wide range of disciplines, from industrial design to gaming, computer graphics and various other forms of digital art. While most traditional methods focus on primitive based model generation, advances in deep learning made it possible to learn 3-dimensional geometric shape representations in an end-to-end manner. However, most current deep learning based frameworks focus on the representation and generation of voxel and point-cloud based shapes, making it not directly applicable to design and graphics communities. This study addresses the needs for automatic generation of mesh-based geometries, and propose a novel framework that utilizes signed distance function representation that generates detail preserving three-dimensional surface mesh by a deep learning based approach.
Tasks
Published	2017-09-22
URL	http://arxiv.org/abs/1709.07581v1
PDF	http://arxiv.org/pdf/1709.07581v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-detail-enhancing-mesh-based
Repo
Framework