July 29, 2019

2884 words 14 mins read

Paper Group ANR 147

Autoencoder-Driven Weather Clustering for Source Estimation during Nuclear Events. Coordinated Online Learning With Applications to Learning User Preferences. Microscopy Cell Segmentation via Adversarial Neural Networks. Aligning Script Events with Narrative Texts. sWSI: A Low-cost and Commercial-quality Whole Slide Imaging System on Android and iO …

Autoencoder-Driven Weather Clustering for Source Estimation during Nuclear Events


Title	Autoencoder-Driven Weather Clustering for Source Estimation during Nuclear Events
Authors	I. A. Klampanos, A. Davvetas, S. Andronopoulos, C. Pappas, A. Ikonomopoulos, V. Karkaletsis
Abstract	Emergency response applications for nuclear or radiological events can be significantly improved via deep feature learning due to the hidden complexity of the data and models involved. In this paper we present a novel methodology for rapid source estimation during radiological releases based on deep feature extraction and weather clustering. Atmospheric dispersions are then calculated based on identified predominant weather patterns and are matched against simulated incidents indicated by radiation readings on the ground. We evaluate the accuracy of our methods over multiple years of weather reanalysis data in the European region. We juxtapose these results with deep classification convolution networks and discuss advantages and disadvantages.
Tasks
Published	2017-09-18
URL	http://arxiv.org/abs/1709.05840v2
PDF	http://arxiv.org/pdf/1709.05840v2.pdf
PWC	https://paperswithcode.com/paper/autoencoder-driven-weather-clustering-for
Repo
Framework

Coordinated Online Learning With Applications to Learning User Preferences


Title	Coordinated Online Learning With Applications to Learning User Preferences
Authors	Christoph Hirnschall, Adish Singla, Sebastian Tschiatschek, Andreas Krause
Abstract	We study an online multi-task learning setting, in which instances of related tasks arrive sequentially, and are handled by task-specific online learners. We consider an algorithmic framework to model the relationship of these tasks via a set of convex constraints. To exploit this relationship, we design a novel algorithm – COOL – for coordinating the individual online learners: Our key idea is to coordinate their parameters via weighted projections onto a convex set. By adjusting the rate and accuracy of the projection, the COOL algorithm allows for a trade-off between the benefit of coordination and the required computation/communication. We derive regret bounds for our approach and analyze how they are influenced by these trade-off factors. We apply our results on the application of learning users’ preferences on the Airbnb marketplace with the goal of incentivizing users to explore under-reviewed apartments.
Tasks	Multi-Task Learning
Published	2017-02-09
URL	http://arxiv.org/abs/1702.02849v1
PDF	http://arxiv.org/pdf/1702.02849v1.pdf
PWC	https://paperswithcode.com/paper/coordinated-online-learning-with-applications
Repo
Framework

Microscopy Cell Segmentation via Adversarial Neural Networks


Title	Microscopy Cell Segmentation via Adversarial Neural Networks
Authors	Assaf Arbelle, Tammy Riklin Raviv
Abstract	We present a novel method for cell segmentation in microscopy images which is inspired by the Generative Adversarial Neural Network (GAN) approach. Our framework is built on a pair of two competitive artificial neural networks, with a unique architecture, termed Rib Cage, which are trained simultaneously and together define a min-max game resulting in an accurate segmentation of a given image. Our approach has two main strengths, similar to the GAN, the method does not require a formulation of a loss function for the optimization process. This allows training on a limited amount of annotated data in a weakly supervised manner. Promising segmentation results on real fluorescent microscopy data are presented. The code is freely available at: https://github.com/arbellea/DeepCellSeg.git
Tasks	Cell Segmentation
Published	2017-09-18
URL	http://arxiv.org/abs/1709.05860v4
PDF	http://arxiv.org/pdf/1709.05860v4.pdf
PWC	https://paperswithcode.com/paper/microscopy-cell-segmentation-via-adversarial
Repo
Framework

Aligning Script Events with Narrative Texts


Title	Aligning Script Events with Narrative Texts
Authors	Simon Ostermann, Michael Roth, Stefan Thater, Manfred Pinkal
Abstract	Script knowledge plays a central role in text understanding and is relevant for a variety of downstream tasks. In this paper, we consider two recent datasets which provide a rich and general representation of script events in terms of paraphrase sets. We introduce the task of mapping event mentions in narrative texts to such script event types, and present a model for this task that exploits rich linguistic representations as well as information on temporal ordering. The results of our experiments demonstrate that this complex task is indeed feasible.
Tasks
Published	2017-10-16
URL	https://arxiv.org/abs/1710.05709v2
PDF	https://arxiv.org/pdf/1710.05709v2.pdf
PWC	https://paperswithcode.com/paper/aligning-script-events-with-narrative-texts
Repo
Framework

sWSI: A Low-cost and Commercial-quality Whole Slide Imaging System on Android and iOS Smartphones


Title	sWSI: A Low-cost and Commercial-quality Whole Slide Imaging System on Android and iOS Smartphones
Authors	Shuoxin Ma, Tan Wang
Abstract	In this paper, scalable Whole Slide Imaging (sWSI), a novel high-throughput, cost-effective and robust whole slide imaging system on both Android and iOS platforms is introduced and analyzed. With sWSI, most mainstream smartphone connected to a optical eyepiece of any manually controlled microscope can be automatically controlled to capture sequences of mega-pixel fields of views that are synthesized into giga-pixel virtual slides. Remote servers carry out the majority of computation asynchronously to support clients running at satisfying frame rates without sacrificing image quality nor robustness. A typical 15x15mm sample can be digitized in 30 seconds with 4X or in 3 minutes with 10X object magnification, costing under $1. The virtual slide quality is considered comparable to existing high-end scanners thus satisfying for clinical usage by surveyed pathologies. The scan procedure with features such as supporting magnification up to 100x, recoding z-stacks, specimen-type-neutral and giving real-time feedback, is deemed work-flow-friendly and reliable.
Tasks
Published	2017-04-01
URL	http://arxiv.org/abs/1704.01088v1
PDF	http://arxiv.org/pdf/1704.01088v1.pdf
PWC	https://paperswithcode.com/paper/swsi-a-low-cost-and-commercial-quality-whole
Repo
Framework

Direct-Manipulation Visualization of Deep Networks


Title	Direct-Manipulation Visualization of Deep Networks
Authors	Daniel Smilkov, Shan Carter, D. Sculley, Fernanda B. Viégas, Martin Wattenberg
Abstract	The recent successes of deep learning have led to a wave of interest from non-experts. Gaining an understanding of this technology, however, is difficult. While the theory is important, it is also helpful for novices to develop an intuitive feel for the effect of different hyperparameters and structural variations. We describe TensorFlow Playground, an interactive, open sourced visualization that allows users to experiment via direct manipulation rather than coding, enabling them to quickly build an intuition about neural nets.
Tasks
Published	2017-08-12
URL	http://arxiv.org/abs/1708.03788v1
PDF	http://arxiv.org/pdf/1708.03788v1.pdf
PWC	https://paperswithcode.com/paper/direct-manipulation-visualization-of-deep
Repo
Framework

Distinguishing Posed and Spontaneous Smiles by Facial Dynamics


Title	Distinguishing Posed and Spontaneous Smiles by Facial Dynamics
Authors	Bappaditya Mandal, David Lee, Nizar Ouarti
Abstract	Smile is one of the key elements in identifying emotions and present state of mind of an individual. In this work, we propose a cluster of approaches to classify posed and spontaneous smiles using deep convolutional neural network (CNN) face features, local phase quantization (LPQ), dense optical flow and histogram of gradient (HOG). Eulerian Video Magnification (EVM) is used for micro-expression smile amplification along with three normalization procedures for distinguishing posed and spontaneous smiles. Although the deep CNN face model is trained with large number of face images, HOG features outperforms this model for overall face smile classification task. Using EVM to amplify micro-expressions did not have a significant impact on classification accuracy, while the normalizing facial features improved classification accuracy. Unlike many manual or semi-automatic methodologies, our approach aims to automatically classify all smiles into either `spontaneous' or` posed’ categories, by using support vector machines (SVM). Experimental results on large UvA-NEMO smile database show promising results as compared to other relevant methods.
Tasks	Optical Flow Estimation, Quantization
Published	2017-01-06
URL	http://arxiv.org/abs/1701.01573v3
PDF	http://arxiv.org/pdf/1701.01573v3.pdf
PWC	https://paperswithcode.com/paper/distinguishing-posed-and-spontaneous-smiles
Repo
Framework

Image Matching via Loopy RNN


Title	Image Matching via Loopy RNN
Authors	Donghao Luo, Bingbing Ni, Yichao Yan, Xiaokang Yang
Abstract	Most existing matching algorithms are one-off algorithms, i.e., they usually measure the distance between the two image feature representation vectors for only one time. In contrast, human’s vision system achieves this task, i.e., image matching, by recursively looking at specific/related parts of both images and then making the final judgement. Towards this end, we propose a novel loopy recurrent neural network (Loopy RNN), which is capable of aggregating relationship information of two input images in a progressive/iterative manner and outputting the consolidated matching score in the final iteration. A Loopy RNN features two uniqueness. First, built on conventional long short-term memory (LSTM) nodes, it links the output gate of the tail node to the input gate of the head node, thus it brings up symmetry property required for matching. Second, a monotonous loss designed for the proposed network guarantees increasing confidence during the recursive matching process. Extensive experiments on several image matching benchmarks demonstrate the great potential of the proposed method.
Tasks
Published	2017-06-10
URL	http://arxiv.org/abs/1706.03190v3
PDF	http://arxiv.org/pdf/1706.03190v3.pdf
PWC	https://paperswithcode.com/paper/image-matching-via-loopy-rnn
Repo
Framework

On the role of words in the network structure of texts: application to authorship attribution


Title	On the role of words in the network structure of texts: application to authorship attribution
Authors	Camilo Akimushkin, Diego R. Amancio, Osvaldo N. Oliveira Jr
Abstract	Well-established automatic analyses of texts mainly consider frequencies of linguistic units, e.g. letters, words and bigrams, while methods based on co-occurrence networks consider the structure of texts regardless of the nodes label (i.e. the words semantics). In this paper, we reconcile these distinct viewpoints by introducing a generalized similarity measure to compare texts which accounts for both the network structure of texts and the role of individual words in the networks. We use the similarity measure for authorship attribution of three collections of books, each composed of 8 authors and 10 books per author. High accuracy rates were obtained with typical values from 90% to 98.75%, much higher than with the traditional the TF-IDF approach for the same collections. These accuracies are also higher than taking only the topology of networks into account. We conclude that the different properties of specific words on the macroscopic scale structure of a whole text are as relevant as their frequency of appearance; conversely, considering the identity of nodes brings further knowledge about a piece of text represented as a network.
Tasks
Published	2017-05-11
URL	http://arxiv.org/abs/1705.04187v1
PDF	http://arxiv.org/pdf/1705.04187v1.pdf
PWC	https://paperswithcode.com/paper/on-the-role-of-words-in-the-network-structure
Repo
Framework

Towards Visual Explanations for Convolutional Neural Networks via Input Resampling


Title	Towards Visual Explanations for Convolutional Neural Networks via Input Resampling
Authors	Benjamin J. Lengerich, Sandeep Konam, Eric P. Xing, Stephanie Rosenthal, Manuela Veloso
Abstract	The predictive power of neural networks often costs model interpretability. Several techniques have been developed for explaining model outputs in terms of input features; however, it is difficult to translate such interpretations into actionable insight. Here, we propose a framework to analyze predictions in terms of the model’s internal features by inspecting information flow through the network. Given a trained network and a test image, we select neurons by two metrics, both measured over a set of images created by perturbations to the input image: (1) magnitude of the correlation between the neuron activation and the network output and (2) precision of the neuron activation. We show that the former metric selects neurons that exert large influence over the network output while the latter metric selects neurons that activate on generalizable features. By comparing the sets of neurons selected by these two metrics, our framework suggests a way to investigate the internal attention mechanisms of convolutional neural networks.
Tasks
Published	2017-07-30
URL	http://arxiv.org/abs/1707.09641v2
PDF	http://arxiv.org/pdf/1707.09641v2.pdf
PWC	https://paperswithcode.com/paper/towards-visual-explanations-for-convolutional
Repo
Framework

Hierarchical Classification for Spoken Arabic Dialect Identification using Prosody: Case of Algerian Dialects


Title	Hierarchical Classification for Spoken Arabic Dialect Identification using Prosody: Case of Algerian Dialects
Authors	Soumia Bougrine, Hadda Cherroun, Djelloul Ziadi
Abstract	In daily communications, Arabs use local dialects which are hard to identify automatically using conventional classification methods. The dialect identification challenging task becomes more complicated when dealing with an under-resourced dialects belonging to a same county/region. In this paper, we start by analyzing statistically Algerian dialects in order to capture their specificities related to prosody information which are extracted at utterance level after a coarse-grained consonant/vowel segmentation. According to these analysis findings, we propose a Hierarchical classification approach for spoken Arabic algerian Dialect IDentification (HADID). It takes advantage from the fact that dialects have an inherent property of naturally structured into hierarchy. Within HADID, a top-down hierarchical classification is applied, in which we use Deep Neural Networks (DNNs) method to build a local classifier for every parent node into the hierarchy dialect structure. Our framework is implemented and evaluated on Algerian Arabic dialects corpus. Whereas, the hierarchy dialect structure is deduced from historic and linguistic knowledges. The results reveal that within {\HD}, the best classifier is DNNs compared to Support Vector Machine. In addition, compared with a baseline Flat classification system, our HADID gives an improvement of 63.5% in term of precision. Furthermore, overall results evidence the suitability of our prosody-based HADID for speaker independent dialect identification while requiring less than 6s test utterances.
Tasks
Published	2017-03-29
URL	http://arxiv.org/abs/1703.10065v1
PDF	http://arxiv.org/pdf/1703.10065v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-classification-for-spoken-arabic
Repo
Framework

A fatal point concept and a low-sensitivity quantitative measure for traffic safety analytics


Title	A fatal point concept and a low-sensitivity quantitative measure for traffic safety analytics
Authors	Shan Suthaharan
Abstract	The variability of the clusters generated by clustering techniques in the domain of latitude and longitude variables of fatal crash data are significantly unpredictable. This unpredictability, caused by the randomness of fatal crash incidents, reduces the accuracy of crash frequency (i.e., counts of fatal crashes per cluster) which is used to measure traffic safety in practice. In this paper, a quantitative measure of traffic safety that is not significantly affected by the aforementioned variability is proposed. It introduces a fatal point – a segment with the highest frequency of fatality – concept based on cluster characteristics and detects them by imposing rounding errors to the hundredth decimal place of the longitude. The frequencies of the cluster and the cluster’s fatal point are combined to construct a low-sensitive quantitative measure of traffic safety for the cluster. The performance of the proposed measure of traffic safety is then studied by varying the parameter k of k-means clustering with the expectation that other clustering techniques can be adopted in a similar fashion. The 2015 North Carolina fatal crash dataset of Fatality Analysis Reporting System (FARS) is used to evaluate the proposed fatal point concept and perform experimental analysis to determine the effectiveness of the proposed measure. The empirical study shows that the average traffic safety, measured by the proposed quantitative measure over several clusters, is not significantly affected by the variability, compared to that of the standard crash frequency.
Tasks
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10131v1
PDF	http://arxiv.org/pdf/1711.10131v1.pdf
PWC	https://paperswithcode.com/paper/a-fatal-point-concept-and-a-low-sensitivity
Repo
Framework

Sequential Randomized Matrix Factorization for Gaussian Processes: Efficient Predictions and Hyper-parameter Optimization


Title	Sequential Randomized Matrix Factorization for Gaussian Processes: Efficient Predictions and Hyper-parameter Optimization
Authors	Shaunak D. Bopardikar, George S. Eskander Ekladious
Abstract	This paper presents a sequential randomized lowrank matrix factorization approach for incrementally predicting values of an unknown function at test points using the Gaussian Processes framework. It is well-known that in the Gaussian processes framework, the computational bottlenecks are the inversion of the (regularized) kernel matrix and the computation of the hyper-parameters defining the kernel. The main contributions of this paper are two-fold. First, we formalize an approach to compute the inverse of the kernel matrix using randomized matrix factorization algorithms in a streaming scenario, i.e., data is generated incrementally over time. The metrics of accuracy and computational efficiency of the proposed method are compared against a batch approach based on use of randomized matrix factorization and an existing streaming approach based on approximating the Gaussian process by a finite set of basis vectors. Second, we extend the sequential factorization approach to a class of kernel functions for which the hyperparameters can be efficiently optimized. All results are demonstrated on two publicly available datasets.
Tasks	Gaussian Processes
Published	2017-11-19
URL	http://arxiv.org/abs/1711.06989v1
PDF	http://arxiv.org/pdf/1711.06989v1.pdf
PWC	https://paperswithcode.com/paper/sequential-randomized-matrix-factorization
Repo
Framework

A Geometric View of Optimal Transportation and Generative Model


Title	A Geometric View of Optimal Transportation and Generative Model
Authors	Na Lei, Kehua Su, Li Cui, Shing-Tung Yau, David Xianfeng Gu
Abstract	In this work, we show the intrinsic relations between optimal transportation and convex geometry, especially the variational approach to solve Alexandrov problem: constructing a convex polytope with prescribed face normals and volumes. This leads to a geometric interpretation to generative models, and leads to a novel framework for generative models. By using the optimal transportation view of GAN model, we show that the discriminator computes the Kantorovich potential, the generator calculates the transportation map. For a large class of transportation costs, the Kantorovich potential can give the optimal transportation map by a close-form formula. Therefore, it is sufficient to solely optimize the discriminator. This shows the adversarial competition can be avoided, and the computational architecture can be simplified. Preliminary experimental results show the geometric method outperforms WGAN for approximating probability measures with multiple clusters in low dimensional space.
Tasks
Published	2017-10-16
URL	http://arxiv.org/abs/1710.05488v2
PDF	http://arxiv.org/pdf/1710.05488v2.pdf
PWC	https://paperswithcode.com/paper/a-geometric-view-of-optimal-transportation
Repo
Framework

Outlier Robust Online Learning


Title	Outlier Robust Online Learning
Authors	Jiashi Feng, Huan Xu, Shie Mannor
Abstract	We consider the problem of learning from noisy data in practical settings where the size of data is too large to store on a single machine. More challenging, the data coming from the wild may contain malicious outliers. To address the scalability and robustness issues, we present an online robust learning (ORL) approach. ORL is simple to implement and has provable robustness guarantee – in stark contrast to existing online learning approaches that are generally fragile to outliers. We specialize the ORL approach for two concrete cases: online robust principal component analysis and online linear regression. We demonstrate the efficiency and robustness advantages of ORL through comprehensive simulations and predicting image tags on a large-scale data set. We also discuss extension of the ORL to distributed learning and provide experimental evaluations.
Tasks
Published	2017-01-01
URL	http://arxiv.org/abs/1701.00251v1
PDF	http://arxiv.org/pdf/1701.00251v1.pdf
PWC	https://paperswithcode.com/paper/outlier-robust-online-learning
Repo
Framework