January 30, 2020

2993 words 15 mins read

Paper Group ANR 248

Learning Quadrangulated Patches For 3D Shape Processing. A Numerical Investigation of the Minimum Width of a Neural Network. Is graph-based feature selection of genes better than random?. Fetal Ultrasound Image Segmentation for Measuring Biometric Parameters Using Multi-Task Deep Learning. Restoring Arabic vowels through omission-tolerant dictionar …

Learning Quadrangulated Patches For 3D Shape Processing


Title	Learning Quadrangulated Patches For 3D Shape Processing
Authors	Kripasindhu Sarkar, Kiran Varanasi, Didier Stricker
Abstract	We propose a system for surface completion and inpainting of 3D shapes using generative models, learnt on local patches. Our method uses a novel encoding of height map based local patches parameterized using 3D mesh quadrangulation of the low resolution input shape. This provides us sufficient amount of local 3D patches to learn a generative model for the task of repairing moderate sized holes. Following the ideas from the recent progress in 2D inpainting, we investigated both linear dictionary based model and convolutional denoising autoencoders based model for the task for inpainting, and show our results to be better than the previous geometry based method of surface inpainting. We validate our method on both synthetic shapes and real world scans.
Tasks	Denoising
Published	2019-03-25
URL	http://arxiv.org/abs/1903.10885v1
PDF	http://arxiv.org/pdf/1903.10885v1.pdf
PWC	https://paperswithcode.com/paper/learning-quadrangulated-patches-for-3d-shape-1
Repo
Framework

A Numerical Investigation of the Minimum Width of a Neural Network


Title	A Numerical Investigation of the Minimum Width of a Neural Network
Authors	Ibrohim Nosirov, Jeffrey M. Hokanson
Abstract	Neural network width and depth are fundamental aspects of network topology. Universal approximation theorems provide that with increasing width or depth, there exists a neural network that approximates a function arbitrarily well. These theorems assume requirements, such as infinite data, that must be discretized in practice. Through numerical experiments, we seek to test the lower bounds established by Hanin in 2017.
Tasks
Published	2019-10-25
URL	https://arxiv.org/abs/1910.13817v1
PDF	https://arxiv.org/pdf/1910.13817v1.pdf
PWC	https://paperswithcode.com/paper/a-numerical-investigation-of-the-minimum
Repo
Framework

Is graph-based feature selection of genes better than random?


Title	Is graph-based feature selection of genes better than random?
Authors	Mohammad Hashir, Paul Bertin, Martin Weiss, Vincent Frappier, Theodore J. Perkins, Geneviève Boucher, Joseph Paul Cohen
Abstract	Gene interaction graphs aim to capture various relationships between genes and represent decades of biology research. When trying to make predictions from genomic data, those graphs could be used to overcome the curse of dimensionality by making machine learning models sparser and more consistent with biological common knowledge. In this work, we focus on assessing whether those graphs capture dependencies seen in gene expression data better than random. We formulate a condition that graphs should satisfy to provide a good prior knowledge and propose to test it using a `Single Gene Inference’ (SGI) task. We compare random graphs with seven major gene interaction graphs published by different research groups, aiming to measure the true benefit of using biologically relevant graphs in this context. Our analysis finds that dependencies can be captured almost as well at random which suggests that, in terms of gene expression levels, the relevant information about the state of the cell is spread across many genes. \|
Tasks	Feature Selection
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09600v3
PDF	https://arxiv.org/pdf/1910.09600v3.pdf
PWC	https://paperswithcode.com/paper/is-graph-biased-feature-selection-of-genes
Repo
Framework

Fetal Ultrasound Image Segmentation for Measuring Biometric Parameters Using Multi-Task Deep Learning


Title	Fetal Ultrasound Image Segmentation for Measuring Biometric Parameters Using Multi-Task Deep Learning
Authors	Zahra Sobhaninia, Shima Rafiei, Ali Emami, Nader Karimi, Kayvan Najarian, Shadrokh Samavi, S. M. Reza Soroushmehr
Abstract	Ultrasound imaging is a standard examination during pregnancy that can be used for measuring specific biometric parameters towards prenatal diagnosis and estimating gestational age. Fetal head circumference (HC) is one of the significant factors to determine the fetus growth and health. In this paper, a multi-task deep convolutional neural network is proposed for automatic segmentation and estimation of HC ellipse by minimizing a compound cost function composed of segmentation dice score and MSE of ellipse parameters. Experimental results on fetus ultrasound dataset in different trimesters of pregnancy show that the segmentation results and the extracted HC match well with the radiologist annotations. The obtained dice scores of the fetal head segmentation and the accuracy of HC evaluations are comparable to the state-of-the-art.
Tasks	Semantic Segmentation
Published	2019-08-31
URL	https://arxiv.org/abs/1909.00273v1
PDF	https://arxiv.org/pdf/1909.00273v1.pdf
PWC	https://paperswithcode.com/paper/fetal-ultrasound-image-segmentation-for
Repo
Framework

Restoring Arabic vowels through omission-tolerant dictionary lookup


Title	Restoring Arabic vowels through omission-tolerant dictionary lookup
Authors	Alexis Amid Neme, Sébastien Paumier
Abstract	Vowels in Arabic are optional orthographic symbols written as diacritics above or below letters. In Arabic texts, typically more than 97 percent of written words do not explicitly show any of the vowels they contain; that is to say, depending on the author, genre and field, less than 3 percent of words include any explicit vowel. Although numerous studies have been published on the issue of restoring the omitted vowels in speech technologies, little attention has been given to this problem in papers dedicated to written Arabic technologies.f In this research, we present Arabic-Unitex, an Arabic Language Resource, with emphasis on vowel representation and encoding. Specifically, we present two dozens of rules formalizing a detailed description of vowel omission in written text. They are typographical rules integrated into large-coverage resources for morphological annotation. For restoring vowels, our resources are capable of identifying words in which the vowels are not shown, as well as words in which the vowels are partially or fully included. By taking into account these rules, our resources are able to compute and restore for each word form a list of compatible fully vowelized candidates through omission-tolerant dictionary lookup. Our program performs the analysis of 5000 words/second for running text (20 pages/second). Based on these comprehensive linguistic resources, we created a spell checker that detects any invalid/misplaced vowel in a fully or partially vowelized form. Finally, our resources provide a lexical coverage of more than 99 percent of the words used in popular newspapers, and restore vowels in words (out of context) simply and efficiently.
Tasks
Published	2019-05-10
URL	https://arxiv.org/abs/1905.04051v1
PDF	https://arxiv.org/pdf/1905.04051v1.pdf
PWC	https://paperswithcode.com/paper/restoring-arabic-vowels-through-omission
Repo
Framework

Un Modelo Ontológico para el Gobierno Electrónico


Title	Un Modelo Ontológico para el Gobierno Electrónico
Authors	Carlos Roberto Brys, José F. Aldana-Montes, David Luis La Red Martínez
Abstract	Decision making often requires information that must be Provided with the rich data format. Addressing these new requirements appropriately makes it necessary for government agencies to orchestrate large amounts of information from different sources and formats, to be efficiently delivered through the devices commonly used by people, such as computers, netbooks, tablets and smartphones. To overcome these problems, a model is proposed for the conceptual representation of the State’s organizational units, seen as georeferenced entities of Electronic Government, based on ontologies designed under the principles of Linked Open Data, which allows the automatic extraction of information through the machines, which supports the process of governmental decision making and gives citizens full access to find and process through mobile technologies.
Tasks	Decision Making
Published	2019-07-04
URL	https://arxiv.org/abs/1907.02964v1
PDF	https://arxiv.org/pdf/1907.02964v1.pdf
PWC	https://paperswithcode.com/paper/un-modelo-ontologico-para-el-gobierno
Repo
Framework

Data-driven simulation for general purpose multibody dynamics using deep neural networks


Title	Data-driven simulation for general purpose multibody dynamics using deep neural networks
Authors	Hee-Sun Choi, Junmo An, Jin-Gyun Kim, Jae-Yoon Jung, Juhwan Choi, Grzegorz Orzechowski, Aki Mikkola, Jin Hwan Choi
Abstract	In this paper, a machine learning-based simulation framework of general-purpose multibody dynamics is introduced. The aim of the framework is to generate a well-trained meta-model of multibody dynamics (MBD) systems. To this end, deep neural network (DNN) is employed to the framework so as to construct data-based meta-model representing multibody systems. Constructing well-defined training data set with time variable is essential to get accurate and reliable motion data such as displacement, velocity, acceleration, and forces. As a result of the introduced approach, the meta-model provides motion estimation of system dynamics without solving the analytical equations of motion. The performance of the proposed DNN meta-modeling was evaluated to represent several MBD systems.
Tasks	Motion Estimation
Published	2019-09-02
URL	https://arxiv.org/abs/1909.02391v1
PDF	https://arxiv.org/pdf/1909.02391v1.pdf
PWC	https://paperswithcode.com/paper/data-driven-simulation-for-general-purpose
Repo
Framework

Boosting Operational DNN Testing Efficiency through Conditioning


Title	Boosting Operational DNN Testing Efficiency through Conditioning
Authors	Zenan Li, Xiaoxing Ma, Chang Xu, Chun Cao, Jingwei Xu, Jian Lü
Abstract	With the increasing adoption of Deep Neural Network (DNN) models as integral parts of software systems, efficient operational testing of DNNs is much in demand to ensure these models’ actual performance in field conditions. A challenge is that the testing often needs to produce precise results with a very limited budget for labeling data collected in field. Viewing software testing as a practice of reliability estimation through statistical sampling, we re-interpret the idea behind conventional structural coverages as conditioning for variance reduction. With this insight we propose an efficient DNN testing method based on the conditioning on the representation learned by the DNN model under testing. The representation is defined by the probability distribution of the output of neurons in the last hidden layer of the model. To sample from this high dimensional distribution in which the operational data are sparsely distributed, we design an algorithm leveraging cross entropy minimization. Experiments with various DNN models and datasets were conducted to evaluate the general efficiency of the approach. The results show that, compared with simple random sampling, this approach requires only about a half of labeled inputs to achieve the same level of precision.
Tasks
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02533v2
PDF	https://arxiv.org/pdf/1906.02533v2.pdf
PWC	https://paperswithcode.com/paper/boosting-operational-dnn-testing-efficiency
Repo
Framework

MAD-TN: A Tool for Measuring Fluency in Human-Robot Collaboration


Title	MAD-TN: A Tool for Measuring Fluency in Human-Robot Collaboration
Authors	Seth Isaacson, Gretchen Rice, James C. Boerkoel Jr
Abstract	Fluency is an important metric in Human-Robot Interaction (HRI) that describes the coordination with which humans and robots collaborate on a task. Fluency is inherently linked to the timing of the task, making temporal constraint networks a promising way to model and measure fluency. We show that the Multi-Agent Daisy Temporal Network (MAD-TN) formulation, which expands on an existing concept of daisy-structured networks, is both an effective model of human-robot collaboration and a natural way to measure a number of existing fluency metrics. The MAD-TN model highlights new metrics that we hypothesize will strongly correlate with human teammates’ perception of fluency.
Tasks
Published	2019-09-14
URL	https://arxiv.org/abs/1909.06675v3
PDF	https://arxiv.org/pdf/1909.06675v3.pdf
PWC	https://paperswithcode.com/paper/mad-tn-a-tool-for-measuring-fluency-in-human
Repo
Framework

Self-supervised Recurrent Neural Network for 4D Abdominal and In-utero MR Imaging


Title	Self-supervised Recurrent Neural Network for 4D Abdominal and In-utero MR Imaging
Authors	Tong Zhang, Laurence H. Jackson, Alena Uus, James R. Clough, Lisa Story, Mary A. Rutherford, Joseph V. Hajnal, Maria Deprez
Abstract	Accurately estimating and correcting the motion artifacts are crucial for 3D image reconstruction of the abdominal and in-utero magnetic resonance imaging (MRI). The state-of-art methods are based on slice-to-volume registration (SVR) where multiple 2D image stacks are acquired in three orthogonal orientations. In this work, we present a novel reconstruction pipeline that only needs one orientation of 2D MRI scans and can reconstruct the full high-resolution image without masking or registration steps. The framework consists of two main stages: the respiratory motion estimation using a self-supervised recurrent neural network, which learns the respiratory signals that are naturally embedded in the asymmetry relationship of the neighborhood slices and cluster them according to a respiratory state. Then, we train a 3D deconvolutional network for super-resolution (SR) reconstruction of the sparsely selected 2D images using integrated reconstruction and total variation loss. We evaluate the classification accuracy on 5 simulated images and compare our results with the SVR method in adult abdominal and in-utero MRI scans. The results show that the proposed pipeline can accurately estimate the respiratory state and reconstruct 4D SR volumes with better or similar performance to the 3D SVR pipeline with less than 20% sparsely selected slices. The method has great potential to transform the 4D abdominal and in-utero MRI in clinical practice.
Tasks	Image Reconstruction, Motion Estimation, Super-Resolution
Published	2019-08-28
URL	https://arxiv.org/abs/1908.10842v1
PDF	https://arxiv.org/pdf/1908.10842v1.pdf
PWC	https://paperswithcode.com/paper/self-supervised-recurrent-neural-network-for
Repo
Framework

Exploring Frequency Domain Interpretation of Convolutional Neural Networks


Title	Exploring Frequency Domain Interpretation of Convolutional Neural Networks
Authors	Zhongfan Jia, Chenglong Bao, Kaisheng Ma
Abstract	Many existing interpretation methods of convolutional neural networks (CNNs) mainly analyze in spatial domain, yet model interpretability in frequency domain has been rarely studied. To the best of our knowledge, there is no study on the interpretation of modern CNNs from the perspective of the frequency proportion of filters. In this work, we analyze the frequency properties of filters in the first layer as it is the entrance of information and relatively more convenient for analysis. By controlling the proportion of different frequency filters in the training stage, the network classification accuracy and model robustness is evaluated and our results reveal that it has a great impact on the robustness to common corruptions. Moreover, a learnable modulation of frequency proportion with perturbation in power spectrum is proposed from the perspective of frequency domain. Experiments on CIFAR-10-C show 10.97% average robustness gains for ResNet-18 with negligible natural accuracy degradation.
Tasks
Published	2019-11-27
URL	https://arxiv.org/abs/1911.12044v2
PDF	https://arxiv.org/pdf/1911.12044v2.pdf
PWC	https://paperswithcode.com/paper/exploring-frequency-domain-interpretation-of
Repo
Framework

Position Paper: From Multi-Agent Pathfinding to Pipe Routing


Title	Position Paper: From Multi-Agent Pathfinding to Pipe Routing
Authors	Gleb Belov, Liron Cohen, Maria Garcia de la Banda, Daniel Harabor, Sven Koenig, Xinrui Wei
Abstract	The 2D Multi-Agent Path Finding (MAPF) problem aims at finding collision-free paths for a number of agents, from a set of start locations to a set of goal positions in a known 2D environment. MAPF has been studied in theoretical computer science, robotics, and artificial intelligence over several decades, due to its importance for robot navigation. It is currently experiencing significant scientific progress due to its relevance in automated warehousing (such as those operated by Amazon) and in other contemporary application areas. In this paper, we demonstrate that many recently developed MAPF algorithms apply more broadly than currently believed in the MAPF research community. In particular, we describe the 3D Pipe Routing (PR) problem, which aims at placing collision-free pipes from given start locations to given goal locations in a known 3D environment. The MAPF and PR problems are similar: a solution to a MAPF instance is a set of blocked cells in x-y-t space, while a solution to the corresponding PR instance is a set of blocked cells in x-y-z space. We show how to use this similarity to apply several recently developed MAPF algorithms to the PR problem, and discuss their performance on abstract PR instances. We also discuss further research necessary to tackle real-world pipe-routing instances of interest to industry today. This opens up a new direction of industrial relevance for the MAPF research community.
Tasks	Multi-Agent Path Finding, Robot Navigation
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08412v1
PDF	https://arxiv.org/pdf/1905.08412v1.pdf
PWC	https://paperswithcode.com/paper/position-paper-from-multi-agent-pathfinding
Repo
Framework

Joint Motion Estimation and Segmentation from Undersampled Cardiac MR Image


Title	Joint Motion Estimation and Segmentation from Undersampled Cardiac MR Image
Authors	Chen Qin, Wenjia Bai, Jo Schlemper, Steffen E. Petersen, Stefan K. Piechnik, Stefan Neubauer, Daniel Rueckert
Abstract	Accelerating the acquisition of magnetic resonance imaging (MRI) is a challenging problem, and many works have been proposed to reconstruct images from undersampled k-space data. However, if the main purpose is to extract certain quantitative measures from the images, perfect reconstructions may not always be necessary as long as the images enable the means of extracting the clinically relevant measures. In this paper, we work on jointly predicting cardiac motion estimation and segmentation directly from undersampled data, which are two important steps in quantitatively assessing cardiac function and diagnosing cardiovascular diseases. In particular, a unified model consisting of both motion estimation branch and segmentation branch is learned by optimising the two tasks simultaneously. Additional corresponding fully-sampled images are incorporated into the network as a parallel sub-network to enhance and guide the learning during the training process. Experimental results using cardiac MR images from 220 subjects show that the proposed model is robust to undersampled data and is capable of predicting results that are close to that from fully-sampled ones, while bypassing the usual image reconstruction stage.
Tasks	Image Reconstruction, Motion Estimation
Published	2019-08-20
URL	https://arxiv.org/abs/1908.07623v1
PDF	https://arxiv.org/pdf/1908.07623v1.pdf
PWC	https://paperswithcode.com/paper/190807623
Repo
Framework

Supervised Learning for Physical Layer based Message Authentication in URLLC scenarios


Title	Supervised Learning for Physical Layer based Message Authentication in URLLC scenarios
Authors	Andreas Weinand, Raja Sattiraju, Michael Karrenbauer, Hans D. Schotten
Abstract	PHYSEC based message authentication can, as an alternative to conventional security schemes, be applied within \gls{urllc} scenarios in order to meet the requirement of secure user data transmissions in the sense of authenticity and integrity. In this work, we investigate the performance of supervised learning classifiers for discriminating legitimate transmitters from illegimate ones in such scenarios. We further present our methodology of data collection using \gls{sdr} platforms and the data processing pipeline including e.g. necessary preprocessing steps. Finally, the performance of the considered supervised learning schemes under different side conditions is presented.
Tasks
Published	2019-09-13
URL	https://arxiv.org/abs/1909.06365v1
PDF	https://arxiv.org/pdf/1909.06365v1.pdf
PWC	https://paperswithcode.com/paper/supervised-learning-for-physical-layer-based
Repo
Framework

3D Object Detection Using Scale Invariant and Feature Reweighting Networks


Title	3D Object Detection Using Scale Invariant and Feature Reweighting Networks
Authors	Xin Zhao, Zhe Liu, Ruolan Hu, Kaiqi Huang
Abstract	3D object detection plays an important role in a large number of real-world applications. It requires us to estimate the localizations and the orientations of 3D objects in real scenes. In this paper, we present a new network architecture which focuses on utilizing the front view images and frustum point clouds to generate 3D detection results. On the one hand, a PointSIFT module is utilized to improve the performance of 3D segmentation. It can capture the information from different orientations in space and the robustness to different scale shapes. On the other hand, our network obtains the useful features and suppresses the features with less information by a SENet module. This module reweights channel features and estimates the 3D bounding boxes more effectively. Our method is evaluated on both KITTI dataset for outdoor scenes and SUN-RGBD dataset for indoor scenes. The experimental results illustrate that our method achieves better performance than the state-of-the-art methods especially when point clouds are highly sparse.
Tasks	3D Object Detection, Object Detection
Published	2019-01-08
URL	http://arxiv.org/abs/1901.02237v1
PDF	http://arxiv.org/pdf/1901.02237v1.pdf
PWC	https://paperswithcode.com/paper/3d-object-detection-using-scale-invariant-and
Repo
Framework