April 2, 2020

2974 words 14 mins read

Paper Group ANR 380

Paper Group ANR 380

Learning Object Scale With Click Supervision for Object Detection. Causal Mosaic: Cause-Effect Inference via Nonlinear ICA and Ensemble Method. Automated Segmentation of Vertebrae on Lateral Chest Radiography Using Deep Learning. A Novel Hybrid GWO with WOA for Global Numerical Optimization and Solving Pressure Vessel Design. CAKES: Channel-wise Au …

Learning Object Scale With Click Supervision for Object Detection

Title Learning Object Scale With Click Supervision for Object Detection
Authors Liao Zhang, Yan Yan, Lin Cheng, Hanzi Wang
Abstract Weakly-supervised object detection has recently attracted increasing attention since it only requires image-levelannotations. However, the performance obtained by existingmethods is still far from being satisfactory compared with fully-supervised object detection methods. To achieve a good trade-off between annotation cost and object detection performance,we propose a simple yet effective method which incorporatesCNN visualization with click supervision to generate the pseudoground-truths (i.e., bounding boxes). These pseudo ground-truthscan be used to train a fully-supervised detector. To estimatethe object scale, we firstly adopt a proposal selection algorithmto preserve high-quality proposals, and then generate ClassActivation Maps (CAMs) for these preserved proposals by theproposed CNN visualization algorithm called Spatial AttentionCAM. Finally, we fuse these CAMs together to generate pseudoground-truths and train a fully-supervised object detector withthese ground-truths. Experimental results on the PASCAL VOC2007 and VOC 2012 datasets show that the proposed methodcan obtain much higher accuracy for estimating the object scale,compared with the state-of-the-art image-level based methodsand the center-click based method
Tasks Object Detection, Weakly Supervised Object Detection
Published 2020-02-20
URL https://arxiv.org/abs/2002.08555v1
PDF https://arxiv.org/pdf/2002.08555v1.pdf
PWC https://paperswithcode.com/paper/learning-object-scale-with-click-supervision

Causal Mosaic: Cause-Effect Inference via Nonlinear ICA and Ensemble Method

Title Causal Mosaic: Cause-Effect Inference via Nonlinear ICA and Ensemble Method
Authors Pengzhou, Wu, Kenji Fukumizu
Abstract We address the problem of distinguishing cause from effect in bivariate setting. Based on recent developments in nonlinear independent component analysis (ICA), we train nonparametrically general nonlinear causal models that allow non-additive noise. Further, we build an ensemble framework, namely Causal Mosaic, which models a causal pair by a mixture of nonlinear models. We compare this method with other recent methods on artificial and real world benchmark datasets, and our method shows state-of-the-art performance.
Published 2020-01-07
URL https://arxiv.org/abs/2001.01894v1
PDF https://arxiv.org/pdf/2001.01894v1.pdf
PWC https://paperswithcode.com/paper/causal-mosaic-cause-effect-inference-via

Automated Segmentation of Vertebrae on Lateral Chest Radiography Using Deep Learning

Title Automated Segmentation of Vertebrae on Lateral Chest Radiography Using Deep Learning
Authors Sanket Badhe, Varun Singh, Joy Li, Paras Lakhani
Abstract The purpose of this study is to develop an automated algorithm for thoracic vertebral segmentation on chest radiography using deep learning. 124 de-identified lateral chest radiographs on unique patients were obtained. Segmentations of visible vertebrae were manually performed by a medical student and verified by a board-certified radiologist. 74 images were used for training, 10 for validation, and 40 were held out for testing. A U-Net deep convolutional neural network was employed for segmentation, using the sum of dice coefficient and binary cross-entropy as the loss function. On the test set, the algorithm demonstrated an average dice coefficient value of 90.5 and an average intersection-over-union (IoU) of 81.75. Deep learning demonstrates promise in the segmentation of vertebrae on lateral chest radiography.
Published 2020-01-05
URL https://arxiv.org/abs/2001.01277v1
PDF https://arxiv.org/pdf/2001.01277v1.pdf
PWC https://paperswithcode.com/paper/automated-segmentation-of-vertebrae-on

A Novel Hybrid GWO with WOA for Global Numerical Optimization and Solving Pressure Vessel Design

Title A Novel Hybrid GWO with WOA for Global Numerical Optimization and Solving Pressure Vessel Design
Authors Hardi M. Mohammed, Tarik A. Rashid
Abstract A recent metaheuristic algorithm, such as Whale Optimization Algorithm (WOA), was proposed. The idea of proposing this algorithm belongs to the hunting behavior of the humpback whale. However, WOA suffers from poor performance in the exploitation phase and stagnates in the local best solution. Grey Wolf Optimization (GWO) is a very competitive algorithm comparing to other common metaheuristic algorithms as it has a super performance in the exploitation phase while it is tested on unimodal benchmark functions. Therefore, the aim of this paper is to hybridize GWO with WOA to overcome the problems. GWO can perform well in exploiting optimal solutions. In this paper, a hybridized WOA with GWO which is called WOAGWO is presented. The proposed hybridized model consists of two steps. Firstly, the hunting mechanism of GWO is embedded into the WOA exploitation phase with a new condition which is related to GWO. Secondly, a new technique is added to the exploration phase to improve the solution after each iteration. Experimentations are tested on three different standard test functions which are called benchmark functions: 23 common functions, 25 CEC2005 functions and 10 CEC2019 functions. The proposed WOAGWO is also evaluated against original WOA, GWO and three other commonly used algorithms. Results show that WOAGWO outperforms other algorithms depending on the Wilcoxon rank-sum test. Finally, WOAGWO is likewise applied to solve an engineering problem such as pressure vessel design. Then the results prove that WOAGWO achieves optimum solution which is better than WOA and Fitness Dependent Optimizer (FDO).
Published 2020-02-28
URL https://arxiv.org/abs/2003.11894v1
PDF https://arxiv.org/pdf/2003.11894v1.pdf
PWC https://paperswithcode.com/paper/a-novel-hybrid-gwo-with-woa-for-global

CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Network

Title CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Network
Authors Qihang Yu, Yingwei Li, Jieru Mei, Yuyin Zhou, Alan L. Yuille
Abstract 3D Convolution Neural Networks (CNNs) have been widely applied to 3D scene understanding, such as video analysis and volumetric image recognition. However, 3D networks can easily lead to over-parameterization which incurs expensive computation cost. In this paper, we propose Channel-wise Automatic KErnel Shrinking (CAKES), to enable efficient 3D learning by shrinking standard 3D convolutions into a set of economic operations (e.g., 1D, 2D convolutions). Unlike previous methods, our proposed CAKES performs channel-wise kernel shrinkage, which enjoys the following benefits: 1) encouraging operations deployed in every layer to be heterogeneous, so that they can extract diverse and complementary information to benefit the learning process; and 2) allowing for an efficient and flexible replacement design, which can be generalized to both spatial-temporal and volumetric data. Together with a neural architecture search framework, by applying CAKES to 3D C2FNAS and ResNet50, we achieve the state-of-the-art performance with much fewer parameters and computational costs on both 3D medical imaging segmentation and video action recognition.
Tasks 3D Medical Imaging Segmentation, Medical Image Segmentation, Neural Architecture Search, Scene Understanding, Temporal Action Localization
Published 2020-03-28
URL https://arxiv.org/abs/2003.12798v1
PDF https://arxiv.org/pdf/2003.12798v1.pdf
PWC https://paperswithcode.com/paper/cakes-channel-wise-automatic-kernel-shrinking

Monte Carlo Game Solver

Title Monte Carlo Game Solver
Authors Tristan Cazenave
Abstract We present a general algorithm to order moves so as to speedup exact game solvers. It uses online learning of playout policies and Monte Carlo Tree Search. The learned policy and the information in the Monte Carlo tree are used to order moves in game solvers. They improve greatly the solving time for multiple games.
Published 2020-01-15
URL https://arxiv.org/abs/2001.05087v1
PDF https://arxiv.org/pdf/2001.05087v1.pdf
PWC https://paperswithcode.com/paper/monte-carlo-game-solver

Sparse and Smooth: improved guarantees for Spectral Clustering in the Dynamic Stochastic Block Model

Title Sparse and Smooth: improved guarantees for Spectral Clustering in the Dynamic Stochastic Block Model
Authors Nicolas Keriven, Samuel Vaiter
Abstract In this paper, we analyse classical variants of the Spectral Clustering (SC) algorithm in the Dynamic Stochastic Block Model (DSBM). Existing results show that, in the relatively sparse case where the expected degree grows logarithmically with the number of nodes, guarantees in the static case can be extended to the dynamic case and yield improved error bounds when the DSBM is sufficiently smooth in time, that is, the communities do not change too much between two time steps. We improve over these results by drawing a new link between the sparsity and the smoothness of the DSBM: the more regular the DSBM is, the more sparse it can be, while still guaranteeing consistent recovery. In particular, a mild condition on the smoothness allows to treat the sparse case with bounded degree. We also extend these guarantees to the normalized Laplacian, and as a by-product of our analysis, we obtain to our knowledge the best spectral concentration bound available for the normalized Laplacian of matrices with independent Bernoulli entries.
Published 2020-02-07
URL https://arxiv.org/abs/2002.02892v2
PDF https://arxiv.org/pdf/2002.02892v2.pdf
PWC https://paperswithcode.com/paper/sparse-and-smooth-improved-guarantees-for

Street-level Travel-time Estimation via Aggregated Uber Data

Title Street-level Travel-time Estimation via Aggregated Uber Data
Authors Kelsey Maass, Arun V Sathanur, Arif Khan, Robert Rallo
Abstract Estimating temporal patterns in travel times along road segments in urban settings is of central importance to traffic engineers and city planners. In this work, we propose a methodology to leverage coarse-grained and aggregated travel time data to estimate the street-level travel times of a given metropolitan area. Our main focus is to estimate travel times along the arterial road segments where relevant data are often unavailable. The central idea of our approach is to leverage easy-to-obtain, aggregated data sets with broad spatial coverage, such as the data published by Uber Movement, as the fabric over which other expensive, fine-grained datasets, such as loop counter and probe data, can be overlaid. Our proposed methodology uses a graph representation of the road network and combines several techniques such as graph-based routing, trip sampling, graph sparsification, and least-squares optimization to estimate the street-level travel times. Using sampled trips and weighted shortest-path routing, we iteratively solve constrained least-squares problems to obtain the travel time estimates. We demonstrate our method on the Los Angeles metropolitan-area street network, where aggregated travel time data is available for trips between traffic analysis zones. Additionally, we present techniques to scale our approach via a novel graph pseudo-sparsification technique.
Published 2020-01-13
URL https://arxiv.org/abs/2001.04533v1
PDF https://arxiv.org/pdf/2001.04533v1.pdf
PWC https://paperswithcode.com/paper/street-level-travel-time-estimation-via

A Novel Framework for Selection of GANs for an Application

Title A Novel Framework for Selection of GANs for an Application
Authors Tanya Motwani, Manojkumar Parmar
Abstract Generative Adversarial Network (GAN) is a current focal point of research. The body of knowledge is fragmented, leading to a trial-error method while selecting an appropriate GAN for a given scenario. We provide a comprehensive summary of the evolution of GANs starting from its inception addressing issues like mode collapse, vanishing gradient, unstable training and non-convergence. We also provide a comparison of various GANs from the application point of view, its behaviour and implementation details. We propose a novel framework to identify candidate GANs for a specific use case based on architecture, loss, regularization and divergence. We also discuss application of the framework using an example, and we demonstrate a significant reduction in search space. This efficient way to determine potential GANs lowers unit economics of AI development for organizations.
Published 2020-02-20
URL https://arxiv.org/abs/2002.08641v1
PDF https://arxiv.org/pdf/2002.08641v1.pdf
PWC https://paperswithcode.com/paper/a-novel-framework-for-selection-of-gans-for

A data-driven choice of misfit function for FWI using reinforcement learning

Title A data-driven choice of misfit function for FWI using reinforcement learning
Authors Bingbing Sun, Tariq Alkhalifah
Abstract In the workflow of Full-Waveform Inversion (FWI), we often tune the parameters of the inversion to help us avoid cycle skipping and obtain high resolution models. For example, typically start by using objective functions that avoid cycle skipping, like tomographic and image based or using only low frequency, and then later, we utilize the least squares misfit to admit high resolution information. We also may perform an isotropic (acoustic) inversion to first update the velocity model and then switch to multi-parameter anisotropic (elastic) inversions to fully recover the complex physics. Such hierarchical approaches are common in FWI, and they often depend on our manual intervention based on many factors, and of course, results depend on experience. However, with the large data size often involved in the inversion and the complexity of the process, making optimal choices is difficult even for an experienced practitioner. Thus, as an example, and within the framework of reinforcement learning, we utilize a deep-Q network (DQN) to learn an optimal policy to determine the proper timing to switch between different misfit functions. Specifically, we train the state-action value function (Q) to predict when to use the conventional L2-norm misfit function or the more advanced optimal-transport matching-filter (OTMF) misfit to mitigate the cycle-skipping and obtain high resolution, as well as improve convergence. We use a simple while demonstrative shifted-signal inversion examples to demonstrate the basic principles of the proposed method.
Published 2020-02-08
URL https://arxiv.org/abs/2002.03154v1
PDF https://arxiv.org/pdf/2002.03154v1.pdf
PWC https://paperswithcode.com/paper/a-data-driven-choice-of-misfit-function-for

Inverse Design of Potential Singlet Fission Molecules using a Transfer Learning Based Approach

Title Inverse Design of Potential Singlet Fission Molecules using a Transfer Learning Based Approach
Authors Akshay Subramanian, Utkarsh Saha, Tejasvini Sharma, Naveen K. Tailor, Soumitra Satapathi
Abstract Singlet fission has emerged as one of the most exciting phenomena known to improve the efficiencies of different types of solar cells and has found uses in diverse optoelectronic applications. The range of available singlet fission molecules is, however, limited as to undergo singlet fission, molecules have to satisfy certain energy conditions. Recent advances in material search using inverse design has enabled the prediction of materials for a wide range of applications and has emerged as one of the most efficient methods in the discovery of suitable materials. It is particularly helpful in manipulating large datasets, uncovering hidden information from the molecular dataset and generating new structures. However, we seldom encounter large datasets in structure prediction problems in material science. In our work, we put forward inverse design of possible singlet fission molecules using a transfer learning based approach where we make use of a much larger ChEMBL dataset of structurally similar molecules to transfer the learned characteristics to the singlet fission dataset.
Tasks Transfer Learning
Published 2020-03-17
URL https://arxiv.org/abs/2003.07666v1
PDF https://arxiv.org/pdf/2003.07666v1.pdf
PWC https://paperswithcode.com/paper/inverse-design-of-potential-singlet-fission

Supervised and Unsupervised Detections for Multiple Object Tracking in Traffic Scenes: A Comparative Study

Title Supervised and Unsupervised Detections for Multiple Object Tracking in Traffic Scenes: A Comparative Study
Authors Hui-Lee Ooi, Guillaume-Alexandre Bilodeau, Nicolas Saunier
Abstract In this paper, we propose a multiple object tracker, called MF-Tracker, that integrates multiple classical features (spatial distances and colours) and modern features (detection labels and re-identification features) in its tracking framework. Since our tracker can work with detections coming either from unsupervised and supervised object detectors, we also investigated the impact of supervised and unsupervised detection inputs in our method and for tracking road users in general. We also compared our results with existing methods that were applied on the UA-Detrac and the UrbanTracker datasets. Results show that our proposed method is performing very well in both datasets with different inputs (MOTA ranging from 0:3491 to 0:5805 for unsupervised inputs on the UrbanTracker dataset and an average MOTA of 0:7638 for supervised inputs on the UA Detrac dataset) under different circumstances. A well-trained supervised object detector can give better results in challenging scenarios. However, in simpler scenarios, if good training data is not available, unsupervised method can perform well and can be a good alternative.
Tasks Multiple Object Tracking, Object Tracking
Published 2020-03-30
URL https://arxiv.org/abs/2003.13644v1
PDF https://arxiv.org/pdf/2003.13644v1.pdf
PWC https://paperswithcode.com/paper/supervised-and-unsupervised-detections-for

Motor Imagery Classification of Single-Arm Tasks Using Convolutional Neural Network based on Feature Refining

Title Motor Imagery Classification of Single-Arm Tasks Using Convolutional Neural Network based on Feature Refining
Authors Byeong-Hoo Lee, Ji-Hoon Jeong, Kyung-Hwan Shim, Dong-Joo Kim
Abstract Brain-computer interface (BCI) decodes brain signals to understand user intention and status. Because of its simple and safe data acquisition process, electroencephalogram (EEG) is commonly used in non-invasive BCI. One of EEG paradigms, motor imagery (MI) is commonly used for recovery or rehabilitation of motor functions due to its signal origin. However, the EEG signals are an oscillatory and non-stationary signal that makes it difficult to collect and classify MI accurately. In this study, we proposed a band-power feature refining convolutional neural network (BFR-CNN) which is composed of two convolution blocks to achieve high classification accuracy. We collected EEG signals to create MI dataset contained the movement imagination of a single-arm. The proposed model outperforms conventional approaches in 4-class MI tasks classification. Hence, we demonstrate that the decoding of user intention is possible by using only EEG signals with robust performance using BFR-CNN.
Tasks EEG
Published 2020-02-04
URL https://arxiv.org/abs/2002.01122v1
PDF https://arxiv.org/pdf/2002.01122v1.pdf
PWC https://paperswithcode.com/paper/motor-imagery-classification-of-single-arm

FrameAxis: Characterizing Framing Bias and Intensity with Word Embedding

Title FrameAxis: Characterizing Framing Bias and Intensity with Word Embedding
Authors Haewoon Kwak, Jisun An, Yong-Yeol Ahn
Abstract We propose FrameAxis, a method of characterizing the framing of a given text by identifying the most relevant semantic axes (“microframes”) defined by antonym word pairs. In contrast to the traditional framing analysis, which has been constrained by a small number of manually annotated general frames, our unsupervised approach provides much more detailed insights, by considering a host of semantic axes. Our method is capable of quantitatively teasing out framing bias – how biased a text is in each microframe – and framing intensity – how much each microframe is used – from the text, offering a nuanced characterization of framing. We evaluate our approach using SemEval datasets as well as three other datasets and human evaluations, demonstrating that FrameAxis can reliably characterize documents with relevant microframes. Our method may allow scalable and nuanced computational analyses of framing across disciplines.
Published 2020-02-20
URL https://arxiv.org/abs/2002.08608v2
PDF https://arxiv.org/pdf/2002.08608v2.pdf
PWC https://paperswithcode.com/paper/frameaxis-characterizing-framing-bias-and

A Survey on Predictive Maintenance for Industry 4.0

Title A Survey on Predictive Maintenance for Industry 4.0
Authors Christian Krupitzer, Tim Wagenhals, Marwin Züfle, Veronika Lesch, Dominik Schäfer, Amin Mozaffarin, Janick Edinger, Christian Becker, Samuel Kounev
Abstract Production issues at Volkswagen in 2016 lead to dramatic losses in sales of up to 400 million Euros per week. This example shows the huge financial impact of a working production facility for companies. Especially in the data-driven domains of Industry 4.0 and Industrial IoT with intelligent, connected machines, a conventional, static maintenance schedule seems to be old-fashioned. In this paper, we present a survey on the current state of the art in predictive maintenance for Industry 4.0. Based on a structured literate survey, we present a classification of predictive maintenance in the context of Industry 4.0 and discuss recent developments in this area.
Published 2020-02-05
URL https://arxiv.org/abs/2002.08224v1
PDF https://arxiv.org/pdf/2002.08224v1.pdf
PWC https://paperswithcode.com/paper/a-survey-on-predictive-maintenance-for
comments powered by Disqus