October 18, 2019

3358 words 16 mins read

Paper Group ANR 607

Onion-Peeling Outlier Detection in 2-D data Sets. State Space Representations of Deep Neural Networks. Cognate-aware morphological segmentation for multilingual neural translation. Learning Compositional Representations for Few-Shot Recognition. Time series kernel similarities for predicting Paroxysmal Atrial Fibrillation from ECGs. Attention-based …

Onion-Peeling Outlier Detection in 2-D data Sets


Title	Onion-Peeling Outlier Detection in 2-D data Sets
Authors	Archit Harsh, John E. Ball, Pan Wei
Abstract	Outlier Detection is a critical and cardinal research task due its array of applications in variety of domains ranging from data mining, clustering, statistical analysis, fraud detection, network intrusion detection and diagnosis of diseases etc. Over the last few decades, distance-based outlier detection algorithms have gained significant reputation as a viable alternative to the more traditional statistical approaches due to their scalable, non-parametric and simple implementation. In this paper, we present a modified onion peeling (Convex hull) genetic algorithm to detect outliers in a Gaussian 2-D point data set. We present three different scenarios of outlier detection using a) Euclidean Distance Metric b) Standardized Euclidean Distance Metric and c) Mahalanobis Distance Metric. Finally, we analyze the performance and evaluate the results.
Tasks	Fraud Detection, Intrusion Detection, Network Intrusion Detection, Outlier Detection
Published	2018-03-12
URL	http://arxiv.org/abs/1803.04964v1
PDF	http://arxiv.org/pdf/1803.04964v1.pdf
PWC	https://paperswithcode.com/paper/onion-peeling-outlier-detection-in-2-d-data
Repo
Framework

State Space Representations of Deep Neural Networks


Title	State Space Representations of Deep Neural Networks
Authors	Michael Hauser, Sean Gunn, Samer Saab Jr, Asok Ray
Abstract	This paper deals with neural networks as dynamical systems governed by differential or difference equations. It shows that the introduction of skip connections into network architectures, such as residual networks and dense networks, turns a system of static equations into a system of dynamical equations with varying levels of smoothness on the layer-wise transformations. Closed form solutions for the state space representations of general dense networks, as well as $k^{th}$ order smooth networks, are found in general settings. Furthermore, it is shown that imposing $k^{th}$ order smoothness on a network architecture with $d$-many nodes per layer increases the state space dimension by a multiple of $k$, and so the effective embedding dimension of the data manifold is $k \cdot d$-many dimensions. It follows that network architectures of these types reduce the number of parameters needed to maintain the same embedding dimension by a factor of $k^2$ when compared to an equivalent first-order, residual network, significantly motivating the development of network architectures of these types. Numerical simulations were run to validate parts of the developed theory.
Tasks
Published	2018-06-11
URL	http://arxiv.org/abs/1806.03751v3
PDF	http://arxiv.org/pdf/1806.03751v3.pdf
PWC	https://paperswithcode.com/paper/state-space-representations-of-deep-neural
Repo
Framework

Cognate-aware morphological segmentation for multilingual neural translation


Title	Cognate-aware morphological segmentation for multilingual neural translation
Authors	Stig-Arne Grönroos, Sami Virpioja, Mikko Kurimo
Abstract	This article describes the Aalto University entry to the WMT18 News Translation Shared Task. We participate in the multilingual subtrack with a system trained under the constrained condition to translate from English to both Finnish and Estonian. The system is based on the Transformer model. We focus on improving the consistency of morphological segmentation for words that are similar orthographically, semantically, and distributionally; such words include etymological cognates, loan words, and proper names. For this, we introduce Cognate Morfessor, a multilingual variant of the Morfessor method. We show that our approach improves the translation quality particularly for Estonian, which has less resources for training the translation model.
Tasks
Published	2018-08-31
URL	http://arxiv.org/abs/1808.10791v1
PDF	http://arxiv.org/pdf/1808.10791v1.pdf
PWC	https://paperswithcode.com/paper/cognate-aware-morphological-segmentation-for
Repo
Framework

Learning Compositional Representations for Few-Shot Recognition


Title	Learning Compositional Representations for Few-Shot Recognition
Authors	Pavel Tokmakov, Yu-Xiong Wang, Martial Hebert
Abstract	One of the key limitations of modern deep learning approaches lies in the amount of data required to train them. Humans, by contrast, can learn to recognize novel categories from just a few examples. Instrumental to this rapid learning ability is the compositional structure of concept representations in the human brain — something that deep learning models are lacking. In this work, we make a step towards bridging this gap between human and machine learning by introducing a simple regularization technique that allows the learned representation to be decomposable into parts. Our method uses category-level attribute annotations to disentangle the feature space of a network into subspaces corresponding to the attributes. These attributes can be either purely visual, like object parts, or more abstract, like openness and symmetry. We demonstrate the value of compositional representations on three datasets: CUB-200-2011, SUN397, and ImageNet, and show that they require fewer examples to learn classifiers for novel categories.
Tasks	Few-Shot Learning
Published	2018-12-21
URL	https://arxiv.org/abs/1812.09213v3
PDF	https://arxiv.org/pdf/1812.09213v3.pdf
PWC	https://paperswithcode.com/paper/learning-compositional-representations-for
Repo
Framework

Time series kernel similarities for predicting Paroxysmal Atrial Fibrillation from ECGs


Title	Time series kernel similarities for predicting Paroxysmal Atrial Fibrillation from ECGs
Authors	Filippo Maria Bianchi, Lorenzo Livi, Alberto Ferrante, Jelena Milosevic, Miroslaw Malek
Abstract	We tackle the problem of classifying Electrocardiography (ECG) signals with the aim of predicting the onset of Paroxysmal Atrial Fibrillation (PAF). Atrial fibrillation is the most common type of arrhythmia, but in many cases PAF episodes are asymptomatic. Therefore, in order to help diagnosing PAF, it is important to design procedures for detecting and, more importantly, predicting PAF episodes. We propose a method for predicting PAF events whose first step consists of a feature extraction procedure that represents each ECG as a multi-variate time series. Successively, we design a classification framework based on kernel similarities for multi-variate time series, capable of handling missing data. We consider different approaches to perform classification in the original space of the multi-variate time series and in an embedding space, defined by the kernel similarity measure. We achieve a classification accuracy comparable with state of the art methods, with the additional advantage of detecting the PAF onset up to 15 minutes in advance.
Tasks	Electrocardiography (ECG), Time Series
Published	2018-01-21
URL	http://arxiv.org/abs/1801.06845v2
PDF	http://arxiv.org/pdf/1801.06845v2.pdf
PWC	https://paperswithcode.com/paper/time-series-kernel-similarities-for
Repo
Framework

Attention-based Pyramid Aggregation Network for Visual Place Recognition


Title	Attention-based Pyramid Aggregation Network for Visual Place Recognition
Authors	Yingying Zhu, Jiong Wang, Lingxi Xie, Liang Zheng
Abstract	Visual place recognition is challenging in the urban environment and is usually viewed as a large scale image retrieval task. The intrinsic challenges in place recognition exist that the confusing objects such as cars and trees frequently occur in the complex urban scene, and buildings with repetitive structures may cause over-counting and the burstiness problem degrading the image representations. To address these problems, we present an Attention-based Pyramid Aggregation Network (APANet), which is trained in an end-to-end manner for place recognition. One main component of APANet, the spatial pyramid pooling, can effectively encode the multi-size buildings containing geo-information. The other one, the attention block, is adopted as a region evaluator for suppressing the confusing regional features while highlighting the discriminative ones. When testing, we further propose a simple yet effective PCA power whitening strategy, which significantly improves the widely used PCA whitening by reasonably limiting the impact of over-counting. Experimental evaluations demonstrate that the proposed APANet outperforms the state-of-the-art methods on two place recognition benchmarks, and generalizes well on standard image retrieval datasets.
Tasks	Image Retrieval, Visual Place Recognition
Published	2018-08-01
URL	http://arxiv.org/abs/1808.00288v1
PDF	http://arxiv.org/pdf/1808.00288v1.pdf
PWC	https://paperswithcode.com/paper/attention-based-pyramid-aggregation-network
Repo
Framework

Psychophysics, Gestalts and Games


Title	Psychophysics, Gestalts and Games
Authors	José Lezama, Samy Blusseau, Jean-Michel Morel, Gregory Randall, Rafael Grompone von Gioi
Abstract	Many psychophysical studies are dedicated to the evaluation of the human gestalt detection on dot or Gabor patterns, and to model its dependence on the pattern and background parameters. Nevertheless, even for these constrained percepts, psychophysics have not yet reached the challenging prediction stage, where human detection would be quantitatively predicted by a (generic) model. On the other hand, Computer Vision has attempted at defining automatic detection thresholds. This chapter sketches a procedure to confront these two methodologies inspired in gestaltism. Using a computational quantitative version of the non-accidentalness principle, we raise the possibility that the psychophysical and the (older) gestaltist setups, both applicable on dot or Gabor patterns, find a useful complement in a Turing test. In our perceptual Turing test, human performance is compared by the scientist to the detection result given by a computer. This confrontation permits to revive the abandoned method of gestaltic games. We sketch the elaboration of such a game, where the subjects of the experiment are confronted to an alignment detection algorithm, and are invited to draw examples that will fool it. We show that in that way a more precise definition of the alignment gestalt and of its computational formulation seems to emerge. Detection algorithms might also be relevant to more classic psychophysical setups, where they can again play the role of a Turing test. To a visual experiment where subjects were invited to detect alignments in Gabor patterns, we associated a single function measuring the alignment detectability in the form of a number of false alarms (NFA). The first results indicate that the values of the NFA, as a function of all simulation parameters, are highly correlated to the human detection. This fact, that we intend to support by further experiments , might end up confirming that human alignment detection is the result of a single mechanism.
Tasks	Human Detection
Published	2018-05-25
URL	http://arxiv.org/abs/1805.10210v1
PDF	http://arxiv.org/pdf/1805.10210v1.pdf
PWC	https://paperswithcode.com/paper/psychophysics-gestalts-and-games
Repo
Framework

Offline Extraction of Indic Regional Language from Natural Scene Image using Text Segmentation and Deep Convolutional Sequence


Title	Offline Extraction of Indic Regional Language from Natural Scene Image using Text Segmentation and Deep Convolutional Sequence
Authors	Sauradip Nag, Pallab Kumar Ganguly, Sumit Roy, Sourab Jha, Krishna Bose, Abhishek Jha, Kousik Dasgupta
Abstract	Regional language extraction from a natural scene image is always a challenging proposition due to its dependence on the text information extracted from Image. Text Extraction on the other hand varies on different lighting condition, arbitrary orientation, inadequate text information, heavy background influence over text and change of text appearance. This paper presents a novel unified method for tackling the above challenges. The proposed work uses an image correction and segmentation technique on the existing Text Detection Pipeline an Efficient and Accurate Scene Text Detector (EAST). EAST uses standard PVAnet architecture to select features and non maximal suppression to detect text from image. Text recognition is done using combined architecture of MaxOut convolution neural network (CNN) and Bidirectional long short term memory (LSTM) network. After recognizing text using the Deep Learning based approach, the native Languages are translated to English and tokenized using standard Text Tokenizers. The tokens that very likely represent a location is used to find the Global Positioning System (GPS) coordinates of the location and subsequently the regional languages spoken in that location is extracted. The proposed method is tested on a self generated dataset collected from Government of India dataset and experimented on Standard Dataset to evaluate the performance of the proposed technique. Comparative study with a few state-of-the-art methods on text detection, recognition and extraction of regional language from images shows that the proposed method outperforms the existing methods.
Tasks
Published	2018-06-16
URL	http://arxiv.org/abs/1806.06208v2
PDF	http://arxiv.org/pdf/1806.06208v2.pdf
PWC	https://paperswithcode.com/paper/offline-extraction-of-indic-regional-language
Repo
Framework

Epistemic Graphs for Representing and Reasoning with Positive and Negative Influences of Arguments


Title	Epistemic Graphs for Representing and Reasoning with Positive and Negative Influences of Arguments
Authors	Anthony Hunter, Sylwia Polberg, Matthias Thimm
Abstract	This paper introduces epistemic graphs as a generalization of the epistemic approach to probabilistic argumentation. In these graphs, an argument can be believed or disbelieved up to a given degree, thus providing a more fine–grained alternative to the standard Dung’s approaches when it comes to determining the status of a given argument. Furthermore, the flexibility of the epistemic approach allows us to both model the rationale behind the existing semantics as well as completely deviate from them when required. Epistemic graphs can model both attack and support as well as relations that are neither support nor attack. The way other arguments influence a given argument is expressed by the epistemic constraints that can restrict the belief we have in an argument with a varying degree of specificity. The fact that we can specify the rules under which arguments should be evaluated and we can include constraints between unrelated arguments permits the framework to be more context–sensitive. It also allows for better modelling of imperfect agents, which can be important in multi–agent applications.
Tasks
Published	2018-02-21
URL	https://arxiv.org/abs/1802.07489v2
PDF	https://arxiv.org/pdf/1802.07489v2.pdf
PWC	https://paperswithcode.com/paper/epistemic-graphs-for-representing-and
Repo
Framework

Accelerate CNN via Recursive Bayesian Pruning


Title	Accelerate CNN via Recursive Bayesian Pruning
Authors	Yuefu Zhou, Ya Zhang, Yanfeng Wang, Qi Tian
Abstract	Channel Pruning, widely used for accelerating Convolutional Neural Networks, is an NP-hard problem due to the inter-layer dependency of channel redundancy. Existing methods generally ignored the above dependency for computation simplicity. To solve the problem, under the Bayesian framework, we here propose a layer-wise Recursive Bayesian Pruning method (RBP). A new dropout-based measurement of redundancy, which facilitate the computation of posterior assuming inter-layer dependency, is introduced. Specifically, we model the noise across layers as a Markov chain and target its posterior to reflect the inter-layer dependency. Considering the closed form solution for posterior is intractable, we derive a sparsity-inducing Dirac-like prior which regularizes the distribution of the designed noise to automatically approximate the posterior. Compared with the existing methods, no additional overhead is required when the inter-layer dependency assumed. The redundant channels can be simply identified by tiny dropout noise and directly pruned layer by layer. Experiments on popular CNN architectures have shown that the proposed method outperforms several state-of-the-arts. Particularly, we achieve up to $\bf{5.0\times}$ and $\bf{2.2\times}$ FLOPs reduction with little accuracy loss on the large scale dataset ILSVRC2012 for VGG16 and ResNet50, respectively.
Tasks
Published	2018-12-02
URL	http://arxiv.org/abs/1812.00353v2
PDF	http://arxiv.org/pdf/1812.00353v2.pdf
PWC	https://paperswithcode.com/paper/network-compression-via-recursive-bayesian
Repo
Framework

Rethinking multiscale cardiac electrophysiology with machine learning and predictive modelling


Title	Rethinking multiscale cardiac electrophysiology with machine learning and predictive modelling
Authors	Chris D. Cantwell, Yumnah Mohamied, Konstantinos N. Tzortzis, Stef Garasto, Charles Houston, Rasheda A. Chowdhury, Fu Siong Ng, Anil A. Bharath, Nicholas S. Peters
Abstract	We review some of the latest approaches to analysing cardiac electrophysiology data using machine learning and predictive modelling. Cardiac arrhythmias, particularly atrial fibrillation, are a major global healthcare challenge. Treatment is often through catheter ablation, which involves the targeted localized destruction of regions of the myocardium responsible for initiating or perpetuating the arrhythmia. Ablation targets are either anatomically defined, or identified based on their functional properties as determined through the analysis of contact intracardiac electrograms acquired with increasing spatial density by modern electroanatomic mapping systems. While numerous quantitative approaches have been investigated over the past decades for identifying these critical curative sites, few have provided a reliable and reproducible advance in success rates. Machine learning techniques, including recent deep-learning approaches, offer a potential route to gaining new insight from this wealth of highly complex spatio-temporal information that existing methods struggle to analyse. Coupled with predictive modelling, these techniques offer exciting opportunities to advance the field and produce more accurate diagnoses and robust personalised treatment. We outline some of these methods and illustrate their use in making predictions from the contact electrogram and augmenting predictive modelling tools, both by more rapidly predicting future states of the system and by inferring the parameters of these models from experimental observations.
Tasks
Published	2018-10-09
URL	http://arxiv.org/abs/1810.04227v1
PDF	http://arxiv.org/pdf/1810.04227v1.pdf
PWC	https://paperswithcode.com/paper/rethinking-multiscale-cardiac
Repo
Framework

On Compressing U-net Using Knowledge Distillation


Title	On Compressing U-net Using Knowledge Distillation
Authors	Karttikeya Mangalam, Mathieu Salzamann
Abstract	We study the use of knowledge distillation to compress the U-net architecture. We show that, while standard distillation is not sufficient to reliably train a compressed U-net, introducing other regularization methods, such as batch normalization and class re-weighting, in knowledge distillation significantly improves the training process. This allows us to compress a U-net by over 1000x, i.e., to 0.1% of its original number of parameters, at a negligible decrease in performance.
Tasks
Published	2018-12-01
URL	http://arxiv.org/abs/1812.00249v1
PDF	http://arxiv.org/pdf/1812.00249v1.pdf
PWC	https://paperswithcode.com/paper/on-compressing-u-net-using-knowledge
Repo
Framework

How is Contrast Encoded in Deep Neural Networks?


Title	How is Contrast Encoded in Deep Neural Networks?
Authors	Arash Akbarinia, Karl R. Gegenfurtner
Abstract	Contrast is a crucial factor in visual information processing. It is desired for a visual system - irrespective of being biological or artificial - to “perceive” the world robustly under large potential changes in illumination. In this work, we studied the responses of deep neural networks (DNN) to identical images at different levels of contrast. We analysed the activation of kernels in the convolutional layers of eight prominent networks with distinct architectures (e.g. VGG and Inception). The results of our experiments indicate that those networks with a higher tolerance to alteration of contrast have more than one convolutional layer prior to the first max-pooling operator. It appears that the last convolutional layer before the first max-pooling acts as a mitigator of contrast variation in input images. In our investigation, interestingly, we observed many similarities between the mechanisms of these DNNs and biological visual systems. These comparisons allow us to understand more profoundly the underlying mechanisms of a visual system that is grounded on the basis of “data-analysis”.
Tasks
Published	2018-09-05
URL	http://arxiv.org/abs/1809.01438v1
PDF	http://arxiv.org/pdf/1809.01438v1.pdf
PWC	https://paperswithcode.com/paper/how-is-contrast-encoded-in-deep-neural
Repo
Framework

Analysis of the generalization error: Empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations


Title	Analysis of the generalization error: Empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
Authors	Julius Berner, Philipp Grohs, Arnulf Jentzen
Abstract	The development of new classification and regression algorithms based on empirical risk minimization (ERM) over deep neural network hypothesis classes, coined Deep Learning, revolutionized the area of artificial intelligence, machine learning, and data analysis. In particular, these methods have been applied to the numerical solution of high-dimensional partial differential equations with great success. Recent simulations indicate that deep learning based algorithms are capable of overcoming the curse of dimensionality for the numerical solution of Kolmogorov equations, which are widely used in models from engineering, finance, and the natural sciences. The present paper considers under which conditions ERM over a deep neural network hypothesis class approximates the solution of a $d$-dimensional Kolmogorov equation with affine drift and diffusion coefficients and typical initial values arising from problems in computational finance up to error $\varepsilon$. We establish that, with high probability over draws of training samples, such an approximation can be achieved with both the size of the hypothesis class and the number of training samples scaling only polynomially in $d$ and $\varepsilon^{-1}$. It can be concluded that ERM over deep neural network hypothesis classes breaks the curse of dimensionality for the numerical solution of linear Kolmogorov equations with affine coefficients.
Tasks
Published	2018-09-09
URL	https://arxiv.org/abs/1809.03062v2
PDF	https://arxiv.org/pdf/1809.03062v2.pdf
PWC	https://paperswithcode.com/paper/analysis-of-the-generalization-error
Repo
Framework

CalibNet: Geometrically Supervised Extrinsic Calibration using 3D Spatial Transformer Networks


Title	CalibNet: Geometrically Supervised Extrinsic Calibration using 3D Spatial Transformer Networks
Authors	Ganesh Iyer, R. Karnik Ram., J. Krishna Murthy, K. Madhava Krishna
Abstract	3D LiDARs and 2D cameras are increasingly being used alongside each other in sensor rigs for perception tasks. Before these sensors can be used to gather meaningful data, however, their extrinsics (and intrinsics) need to be accurately calibrated, as the performance of the sensor rig is extremely sensitive to these calibration parameters. A vast majority of existing calibration techniques require significant amounts of data and/or calibration targets and human effort, severely impacting their applicability in large-scale production systems. We address this gap with CalibNet: a self-supervised deep network capable of automatically estimating the 6-DoF rigid body transformation between a 3D LiDAR and a 2D camera in real-time. CalibNet alleviates the need for calibration targets, thereby resulting in significant savings in calibration efforts. During training, the network only takes as input a LiDAR point cloud, the corresponding monocular image, and the camera calibration matrix K. At train time, we do not impose direct supervision (i.e., we do not directly regress to the calibration parameters, for example). Instead, we train the network to predict calibration parameters that maximize the geometric and photometric consistency of the input images and point clouds. CalibNet learns to iteratively solve the underlying geometric problem and accurately predicts extrinsic calibration parameters for a wide range of mis-calibrations, without requiring retraining or domain adaptation. The project page is hosted at https://epiception.github.io/CalibNet
Tasks	Calibration, Domain Adaptation
Published	2018-03-22
URL	https://arxiv.org/abs/1803.08181v2
PDF	https://arxiv.org/pdf/1803.08181v2.pdf
PWC	https://paperswithcode.com/paper/calibnet-self-supervised-extrinsic
Repo
Framework