January 30, 2020

3011 words 15 mins read

Paper Group ANR 403

Efficient Kernel-based Subsequence Search for User Identification from Walking Activity. Unsupervised Construction of Knowledge Graphs From Text and Code. Quantifying error contributions of computational steps, algorithms and hyperparameter choices in image classification pipelines. Bayesian Receiver Operating Characteristic Metric for Linear Class …

Efficient Kernel-based Subsequence Search for User Identification from Walking Activity


Title	Efficient Kernel-based Subsequence Search for User Identification from Walking Activity
Authors	Antonio Candelieri, Stanislav Fedorov, Enza Messina
Abstract	This paper presents an efficient approach for subsequence search in data streams. The problem consists in identifying coherent repetitions of a given reference time-series, eventually multi-variate, within a longer data stream. Dynamic Time Warping (DTW) is the metric most widely used to implement pattern query, but its computational complexity is a well-known issue. In this paper we present an approach aimed at learning a kernel able to approximate DTW to be used for efficiently analyse streaming data collected from wearable sensors, reducing the burden of computation. Contrary to kernel, DTW allows for comparing time series with different length. Thus, to use a kernel, a feature embedding is used to represent a time-series as a fixed length vector. Each vector component is the DTW between the given time-series and a set of ‘basis’ series, usually randomly chosen. The vector size is the number of basis series used for the feature embedding. Searching for the portion of the data stream minimizing the DTW with the reference subsequence leads to a global optimization problem. The proposed approach has been validated on a benchmark dataset related to the identification of users depending on their walking activity. A comparison with a traditional DTW implementation is also provided.
Tasks	Time Series
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04680v2
PDF	https://arxiv.org/pdf/1906.04680v2.pdf
PWC	https://paperswithcode.com/paper/efficient-kernel-based-subsequence-search-for
Repo
Framework

Unsupervised Construction of Knowledge Graphs From Text and Code


Title	Unsupervised Construction of Knowledge Graphs From Text and Code
Authors	Kun Cao, James Fairbanks
Abstract	The scientific literature is a rich source of information for data mining with conceptual knowledge graphs; the open science movement has enriched this literature with complementary source code that implements scientific models. To exploit this new resource, we construct a knowledge graph using unsupervised learning methods to identify conceptual entities. We associate source code entities to these natural language concepts using word embedding and clustering techniques. Practical naming conventions for methods and functions tend to reflect the concept(s) they implement. We take advantage of this specificity by presenting a novel process for joint clustering text concepts that combines word-embeddings, nonlinear dimensionality reduction, and clustering techniques to assist in understanding, organizing, and comparing software in the open science ecosystem. With our pipeline, we aim to assist scientists in building on existing models in their discipline when making novel models for new phenomena. By combining source code and conceptual information, our knowledge graph enhances corpus-wide understanding of scientific literature.
Tasks	Dimensionality Reduction, Knowledge Graphs, Word Embeddings
Published	2019-08-25
URL	https://arxiv.org/abs/1908.09354v1
PDF	https://arxiv.org/pdf/1908.09354v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-construction-of-knowledge-graphs
Repo
Framework

Quantifying error contributions of computational steps, algorithms and hyperparameter choices in image classification pipelines


Title	Quantifying error contributions of computational steps, algorithms and hyperparameter choices in image classification pipelines
Authors	Aritra Chowdhury, Malik Magdin-Ismail, Bulent Yener
Abstract	Data science relies on pipelines that are organized in the form of interdependent computational steps. Each step consists of various candidate algorithms that maybe used for performing a particular function. Each algorithm consists of several hyperparameters. Algorithms and hyperparameters must be optimized as a whole to produce the best performance. Typical machine learning pipelines typically consist of complex algorithms in each of the steps. Not only is the selection process combinatorial, but it is also important to interpret and understand the pipelines. We propose a method to quantify the importance of different layers in the pipeline, by computing an error contribution relative to an agnostic choice of algorithms in that layer. We demonstrate our methodology on image classification pipelines. The agnostic methodology quantifies the error contributions from the computational steps, algorithms and hyperparameters in the image classification pipeline. We show that algorithm selection and hyper-parameter optimization methods can be used to quantify the error contribution and that random search is able to quantify the contribution more accurately than Bayesian optimization. This methodology can be used by domain experts to understand machine learning and data analysis pipelines in terms of their individual components, which can help in prioritizing different components of the pipeline.
Tasks	Image Classification
Published	2019-02-25
URL	http://arxiv.org/abs/1903.02521v1
PDF	http://arxiv.org/pdf/1903.02521v1.pdf
PWC	https://paperswithcode.com/paper/quantifying-error-contributions-of
Repo
Framework

Bayesian Receiver Operating Characteristic Metric for Linear Classifiers


Title	Bayesian Receiver Operating Characteristic Metric for Linear Classifiers
Authors	Syeda Sakira Hassan, Heikki Huttunen, Jari Niemi, Jussi Tohka
Abstract	We propose a novel classifier accuracy metric: the Bayesian Area Under the Receiver Operating Characteristic Curve (CBAUC). The method estimates the area under the ROC curve and is related to the recently proposed Bayesian Error Estimator. The metric can assess the quality of a classifier using only the training dataset without the need for computationally expensive cross-validation. We derive a closed-form solution of the proposed accuracy metric for any linear binary classifier under the Gaussianity assumption, and study the accuracy of the proposed estimator using simulated and real-world data. These experiments confirm that the closed-form CBAUC is both faster and more accurate than conventional AUC estimators.
Tasks
Published	2019-08-23
URL	https://arxiv.org/abs/1908.08771v1
PDF	https://arxiv.org/pdf/1908.08771v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-receiver-operating-characteristic
Repo
Framework

Tale of tails using rule augmented sequence labeling for event extraction


Title	Tale of tails using rule augmented sequence labeling for event extraction
Authors	Ayush Maheshwari, Hrishikesh Patel, Nandan Rathod, Ritesh Kumar, Ganesh Ramakrishnan, Pushpak Bhattacharyya
Abstract	The problem of event extraction is a relatively difficult task for low resource languages due to the non-availability of sufficient annotated data. Moreover, the task becomes complex for tail (rarely occurring) labels wherein extremely less data is available. In this paper, we present a new dataset (InDEE-2019) in the disaster domain for multiple Indic languages, collected from news websites. Using this dataset, we evaluate several rule-based mechanisms to augment deep learning based models. We formulate our problem of event extraction as a sequence labeling task and perform extensive experiments to study and understand the effectiveness of different approaches. We further show that tail labels can be easily incorporated by creating new rules without the requirement of large annotated data.
Tasks
Published	2019-08-19
URL	https://arxiv.org/abs/1908.07018v3
PDF	https://arxiv.org/pdf/1908.07018v3.pdf
PWC	https://paperswithcode.com/paper/tale-of-tails-using-rule-augmented-sequence
Repo
Framework

3D-GMNet: Learning to Estimate 3D Shape from A Single Image As A Gaussian Mixture


Title	3D-GMNet: Learning to Estimate 3D Shape from A Single Image As A Gaussian Mixture
Authors	Kohei Yamashita, Shohei Nobuhara, Ko Nishino
Abstract	In this paper, we introduce 3D-GMNet, a deep neural network for single-image 3D shape recovery. As the name suggests, 3D-GMNet recovers 3D shape as a Gaussian mixture model. In contrast to voxels, point clouds, or meshes, a Gaussian mixture representation requires a much smaller footprint for representing 3D shapes and, at the same time, offers a number of additional advantages including instant pose estimation, automatic level-of-detail computation, and a distance measure. The proposed 3D-GMNet is trained end-to-end with single input images and corresponding 3D models by using two novel loss functions: a 3D Gaussian mixture loss and a multi-view 2D loss. The first maximizes the likelihood of the Gaussian mixture shape representation by considering the target point cloud as samples from the true distribution, and the latter improves the consistency between the input silhouette and the projection of the Gaussian mixture shape model. Extensive quantitative evaluations with synthesized and real images demonstrate the effectiveness of the proposed method.
Tasks	Pose Estimation
Published	2019-12-10
URL	https://arxiv.org/abs/1912.04663v1
PDF	https://arxiv.org/pdf/1912.04663v1.pdf
PWC	https://paperswithcode.com/paper/3d-gmnet-learning-to-estimate-3d-shape-from-a
Repo
Framework

A Vietnamese Question Answering System


Title	A Vietnamese Question Answering System
Authors	Dai Quoc Nguyen, Dat Quoc Nguyen, Son Bao Pham
Abstract	Question answering systems aim to produce exact answers to users’ questions instead of a list of related documents as used by current search engines. In this paper, we propose an ontology-based Vietnamese question answering system that allows users to express their questions in natural language. To the best of our knowledge, this is the first attempt to enable users to query an ontological knowledge base using Vietnamese natural language. Experiments of our system on an organizational ontology show promising results.
Tasks	Question Answering
Published	2019-11-26
URL	https://arxiv.org/abs/1911.12267v1
PDF	https://arxiv.org/pdf/1911.12267v1.pdf
PWC	https://paperswithcode.com/paper/a-vietnamese-question-answering-system
Repo
Framework

Learning Autocomplete Systems as a Communication Game


Title	Learning Autocomplete Systems as a Communication Game
Authors	Mina Lee, Tatsunori B. Hashimoto, Percy Liang
Abstract	We study textual autocomplete—the task of predicting a full sentence from a partial sentence—as a human-machine communication game. Specifically, we consider three competing goals for effective communication: use as few tokens as possible (efficiency), transmit sentences faithfully (accuracy), and be learnable to humans (interpretability). We propose an unsupervised approach which tackles all three desiderata by constraining the communication scheme to keywords extracted from a source sentence for interpretability and optimizing the efficiency-accuracy tradeoff. Our experiments show that this approach results in an autocomplete system that is 52% more accurate at a given efficiency level compared to baselines, is robust to user variations, and saves time by nearly 50% compared to typing full sentences.
Tasks
Published	2019-11-16
URL	https://arxiv.org/abs/1911.06964v1
PDF	https://arxiv.org/pdf/1911.06964v1.pdf
PWC	https://paperswithcode.com/paper/learning-autocomplete-systems-as-a
Repo
Framework

Fast Inference in Capsule Networks Using Accumulated Routing Coefficients


Title	Fast Inference in Capsule Networks Using Accumulated Routing Coefficients
Authors	Zhen Zhao, Ashley Kleinhans, Gursharan Sandhu, Ishan Patel, K. P. Unnikrishnan
Abstract	We present a method for fast inference in Capsule Networks (CapsNets) by taking advantage of a key insight regarding the routing coefficients that link capsules between adjacent network layers. Since the routing coefficients are responsible for assigning object parts to wholes, and an object whole generally contains similar intra-class and dissimilar inter-class parts, the routing coefficients tend to form a unique signature for each object class. For fast inference, a network is first trained in the usual manner using examples from the training dataset. Afterward, the routing coefficients associated with the training examples are accumulated offline and used to create a set of “master” routing coefficients. During inference, these master routing coefficients are used in place of the dynamically calculated routing coefficients. Our method effectively replaces the for-loop iterations in the dynamic routing procedure with a single matrix multiply operation, providing a significant boost in inference speed. Compared with the dynamic routing procedure, fast inference decreases the test accuracy for the MNIST, Background MNIST, Fashion MNIST, and Rotated MNIST datasets by less than 0.5% and by approximately 5% for CIFAR10.
Tasks
Published	2019-04-15
URL	http://arxiv.org/abs/1904.07304v1
PDF	http://arxiv.org/pdf/1904.07304v1.pdf
PWC	https://paperswithcode.com/paper/fast-inference-in-capsule-networks-using
Repo
Framework

A Reinforced Generation of Adversarial Samples for Neural Machine Translation


Title	A Reinforced Generation of Adversarial Samples for Neural Machine Translation
Authors	Wei Zou, Shujian Huang, Jun Xie, Xinyu Dai, Jiajun Chen
Abstract	Neural machine translation systems tend to fail on less de-cent inputs despite its great efficacy, which may greatly harm the credibility of these systems. Fathoming how and when neural-based systems fail in such cases is critical for industrial maintenance. Instead of collecting and analyzing bad cases using limited handcrafted error features, here we investigate this issue by generating adversarial samples via a new paradigm based on reinforcement learning. Our paradigm could expose pitfalls for a given performance metric, e.g.BLEU, and could target any given neural machine translation architecture. We conduct experiments of adversarial attacks on two mainstream neural machine translation architectures, RNN-search and Transformer. The results show that our method efficiently produces stable attacks with meaning-preserving adversarial samples. We also present a qualitative and quantitative analysis for the preference pattern of the attack, showing its capability of pitfall exposure.
Tasks	Machine Translation
Published	2019-11-09
URL	https://arxiv.org/abs/1911.03677v1
PDF	https://arxiv.org/pdf/1911.03677v1.pdf
PWC	https://paperswithcode.com/paper/a-reinforced-generation-of-adversarial
Repo
Framework

RIU-Net: Embarrassingly simple semantic segmentation of 3D LiDAR point cloud


Title	RIU-Net: Embarrassingly simple semantic segmentation of 3D LiDAR point cloud
Authors	Pierre Biasutti, Aurélie Bugeau, Jean-François Aujol, Mathieu Brédif
Abstract	This paper proposes RIU-Net (for Range-Image U-Net), the adaptation of a popular semantic segmentation network for the semantic segmentation of a 3D LiDAR point cloud. The point cloud is turned into a 2D range-image by exploiting the topology of the sensor. This image is then used as input to a U-net. This architecture has already proved its efficiency for the task of semantic segmentation of medical images. We demonstrate how it can also be used for the accurate semantic segmentation of a 3D LiDAR point cloud and how it represents a valid bridge between image processing and 3D point cloud processing. Our model is trained on range-images built from KITTI 3D object detection dataset. Experiments show that RIU-Net, despite being very simple, offers results that are comparable to the state-of-the-art of range-image based methods. Finally, we demonstrate that this architecture is able to operate at 90fps on a single GPU, which enables deployment for real-time segmentation.
Tasks	3D Object Detection, Object Detection, Semantic Segmentation
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08748v3
PDF	https://arxiv.org/pdf/1905.08748v3.pdf
PWC	https://paperswithcode.com/paper/riu-net-embarrassingly-simple-semantic
Repo
Framework

A generalization of the symmetrical and optimal probability-to-possibility transformations


Title	A generalization of the symmetrical and optimal probability-to-possibility transformations
Authors	Esteve del Acebo, Yousef Alizadeh-Q, Sayyed Ali Hossayni
Abstract	Possibility and probability theories are alternative and complementary ways to deal with uncertainty, which has motivated over the last years an interest for the study of ways to transform probability distributions into possibility distributions and conversely. This paper studies the advantages and shortcomings of two well-known discrete probability to possibility transformations: the optimal transformation and the symmetrical transformation, and presents a novel parametric family of probability to possibility transformations which generalizes them and alleviate their shortcomings, showing a big potential for practical application. The paper also introduces a novel fuzzy measure of specificity for probability distributions based on the concept of fuzzy subsethood and presents a empirical validation of the generalized transformation usefulness applying it to the text authorship attribution problem.
Tasks
Published	2019-12-29
URL	https://arxiv.org/abs/2001.00007v1
PDF	https://arxiv.org/pdf/2001.00007v1.pdf
PWC	https://paperswithcode.com/paper/a-generalization-of-the-symmetrical-and
Repo
Framework

Beneficial perturbation network for continual learning


Title	Beneficial perturbation network for continual learning
Authors	Shixian Wen, Laurent Itti
Abstract	Sequential learning of multiple tasks in artificial neural networks using gradient descent leads to catastrophic forgetting, whereby previously learned knowledge is erased during learning of new, disjoint knowledge. Here, we propose a fundamentally new type of method - Beneficial Perturbation Network (BPN). We add task-dependent memory (biasing) units to allow the network to operate in different regimes for different tasks. We compute the most beneficial directions to train these units, in a manner inspired by recent work on adversarial examples. At test time, beneficial perturbations for a given task bias the network toward that task to overcome catastrophic forgetting. BPN is not only more parameter-efficient than network expansion methods, but also does not need to store any data from previous tasks, in contrast with episodic memory methods. Experiments on variants of the MNIST, CIFAR-10, CIFAR-100 datasets demonstrate strong performance of BPN when compared to the state-of-the-art.
Tasks	Continual Learning
Published	2019-06-22
URL	https://arxiv.org/abs/1906.10528v1
PDF	https://arxiv.org/pdf/1906.10528v1.pdf
PWC	https://paperswithcode.com/paper/beneficial-perturbation-network-for-continual
Repo
Framework

Non-Invasive MGMT Status Prediction in GBM Cancer Using Magnetic Resonance Images (MRI) Radiomics Features: Univariate and Multivariate Machine Learning Radiogenomics Analysis


Title	Non-Invasive MGMT Status Prediction in GBM Cancer Using Magnetic Resonance Images (MRI) Radiomics Features: Univariate and Multivariate Machine Learning Radiogenomics Analysis
Authors	Ghasem Hajianfar, Isaac Shiri, Hassan Maleki, Niki Oveisi, Abbass Haghparast, Hamid Abdollahi, Mehrdad Oveisi
Abstract	Background and aim: This study aimed to predict methylation status of the O-6 methyl guanine-DNA methyl transferase (MGMT) gene promoter status by using MRI radiomics features, as well as univariate and multivariate analysis. Material and Methods: Eighty-two patients who had a MGMT methylation status were include in this study. Tumor were manually segmented in the four regions of MR images, a) whole tumor, b) active/enhanced region, c) necrotic regions and d) edema regions (E). About seven thousand radiomics features were extracted for each patient. Feature selection and classifier were used to predict MGMT status through different machine learning algorithms. The area under the curve (AUC) of receiver operating characteristic (ROC) curve was used for model evaluations. Results: Regarding univariate analysis, the Inverse Variance feature from gray level co-occurrence matrix (GLCM) in Whole Tumor segment with 4.5 mm Sigma of Laplacian of Gaussian filter with AUC: 0.71 (p-value: 0.002) was found to be the best predictor. For multivariate analysis, the decision tree classifier with Select from Model feature selector and LOG filter in Edema region had the highest performance (AUC: 0.78), followed by Ada Boost classifier with Select from Model feature selector and LOG filter in Edema region (AUC: 0.74). Conclusion: This study showed that radiomics using machine learning algorithms is a feasible, noninvasive approach to predict MGMT methylation status in GBM cancer patients Keywords: Radiomics, Radiogenomics, GBM, MRI, MGMT
Tasks	Feature Selection
Published	2019-07-08
URL	https://arxiv.org/abs/1907.03495v1
PDF	https://arxiv.org/pdf/1907.03495v1.pdf
PWC	https://paperswithcode.com/paper/non-invasive-mgmt-status-prediction-in-gbm
Repo
Framework

Learning Orientation-Estimation Convolutional Neural Network for Building Detection in Optical Remote Sensing Image


Title	Learning Orientation-Estimation Convolutional Neural Network for Building Detection in Optical Remote Sensing Image
Authors	Yongliang Chen
Abstract	Benefiting from the great success of deep learning in computer vision, CNN-based object detection methods have drawn significant attentions. Various frameworks have been proposed which show awesome and robust performance for a large range of datasets. However, for building detection in remote sensing images, buildings always pose a diversity of orientations which makes it a challenge for the application of off-the-shelf methods to building detection. In this work, we aim to integrate orientation regression into the popular axis-aligned bounding-box detection method to tackle this problem. To adapt the axis-aligned bounding boxes to arbitrarily orientated ones, we also develop an algorithm to estimate the Intersection over Union (IoU) overlap between any two arbitrarily oriented boxes which is convenient to implement in Graphics Processing Unit (GPU) for accelerating computation. The proposed method utilizes CNN for both robust feature extraction and rotated bounding box regression. We present our modelin an end-to-end fashion making it easy to train. The model is formulated and trained to predict orientation, location and extent simultaneously obtaining tighter bounding box and hence, higher mean average precision (mAP). Experiments on remote sensing images of different scales shows a promising performance over the conventional one.
Tasks	Object Detection
Published	2019-03-14
URL	http://arxiv.org/abs/1903.05862v1
PDF	http://arxiv.org/pdf/1903.05862v1.pdf
PWC	https://paperswithcode.com/paper/learning-orientation-estimation-convolutional
Repo
Framework