检索结果-内蒙古大学图书馆

6th Asian Conference on Machine learning, ACML 2014

作者： Canévet, Olivier Lefakis, Leonidas Fleuret, François Computer Vision and Learning group Idiap Research Institute Martigny Switzerland École Polytechnique Fédérale de Lausanne Lausanne Switzerland

We propose a novel approach to efficiently select informative samples for large-scale learning. Instead of directly feeding a learning algorithm with a very large amount of samples, as it is usually done to reach state-of-the-art performance, we have developed a "distillation" procedure to recursively reduce the size of an initial training set using a criterion that ensures the maximization of the information content of the selected sub-set. We demonstrate the performance of this procedure for two different computer vision problems. First, we show that distillation can be used to improve the traditional bootstrapping approach to object detection. Second, we apply distillation to a classification problem with artificial distortions. We show that in both cases, using the result of a distillation process instead of a random sub-set taken uniformly in the original sample set improves performance significantly. © 2014 O. Canévet, L. Lefakis & F. Fleuret.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Efficient sample mining for object detection 6

Efficient sample mining for object detection

引用

6th Asian Conference on Machine learning, ACML 2014

作者： Canévet, Olivier Fleuret, François Computer Vision and Learning group Idiap Research Institute Martigny Switzerland École Polytechnique Fédérale de Lausanne Lausanne Switzerland

Object detectors based on the sliding window technique are usually trained in two successive steps: first, an initial classifier is trained on a population of positive samples (i.e. images of the object to detect) and negative samples randomly extracted from scenes which do not contain the object to detect. Then, the scenes are scanned with that initial classifier to enrich the initial set with negative samples incorrectly classified as positive. This bootstrapping process provides the learning algorithm with "hard" samples, which help to improve the decision boundary. Little work has been done on how to efficiently enrich the training set. While the standard bootstrapping approach densely visits the scenes, we propose to evaluate which regions of scenes can be discarded without any further computation to concentrate the search on promising areas. We apply our method to two standard object detection settings, pedestrian and face detection, and show that it provides a multi-fold speed up. © 2014 O. Canévet & F. Fleuret.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

LETHA: learning from high quality inputs for 3D pose estimation in low quality images 2

LETHA: Learning from high quality inputs for 3D pose estimat...

引用

2014 2nd International Conference on 3D vision, 3DV 2014

作者： Penate-Sanchez, Adrianrr Moreno-Noguer, Francesc Andrade-Cetto, Juan Fleuret, François Institut de Robòtica i Informàtica Industrial CSIC-UPC Barcelona Spain Computer Vision and Learning Group Idiap Research Institute Martigny Switzerland École Polytechnique Fédérale de Lausanne Lausanne Switzerland

ISBN: (纸本)9781479970018

We introduce LETHA (learning on Easy data, Test on Hard), a new learning paradigm consisting of building strong priors from high quality training data, and combining them with discriminative machine learning to deal with lowquality test data. Our main contribution is an implementation of that concept for pose estimation. We first automatically build a 3D model of the object of interest from high-definition images, and devise from it a pose-indexed feature extraction scheme. We then train a single classifier to process these feature vectors. Given a low quality test image, we visit many hypothetical poses, extract features consistently and evaluate the response of the classifier. Since this process uses locations recorded during learning, it does not require matching points anymore. We use a boosting procedure to train this classifier common to all poses, which is able to deal with missing features, due in this context to self-occlusion. Our results demonstrate that the method combines the strengths of global image representations, discriminative even for very tiny images, and the robustness to occlusions of approaches based on local feature point descriptors. © 2014 IEEE.

关键词： Image representation

来源：评论

学校读者我要写书评

暂无评论

Mapping geographical inequalities in childhood diarrhoeal morbidity and mortality in low-income and middle-income countries, 2000-17: analysis for the Global Burden of Disease Study 2017 (vol 395, pg 1779, 2020)

引用

LANCET 2020年第10239期395卷 1762-1762页

作者： Reiner, R. C., Jr. Hay, S., I Institute for Health Metrics and Evaluation University of Washington Seattle WA United States Department of Global Health School of Medicine University of Washington Seattle WA United States Department of Health Metrics Sciences School of Medicine University of Washington Seattle WA United States College of Health and Medical Sciences Haramaya University Harar Ethiopia Department of Epidemiology and Biostatistics Haramaya University Harar Ethiopia Department of Medical Laboratory Sciences Haramaya University Harar Ethiopia School of Nursing and Midwifery Haramaya University Harar Ethiopia School of Pharmacy Haramaya University Harar Ethiopia School of Public Health Haramaya University Harar Ethiopia Haramaya University Harar Ethiopia Advanced Diagnostic and Interventional Radiology Research Center Tehran University of Medical Sciences Tehran Iran Cancer Biology Research Center Tehran University of Medical Sciences Tehran Iran Cancer Research Institute Tehran University of Medical Sciences Tehran Iran Department of Economics and Management Sciences for Health Tehran University of Medical Sciences Tehran Iran Department of Environmental Health Engineering Tehran University of Medical Sciences Tehran Iran Department of Epidemiology and Biostatistics Tehran University of Medical Sciences Tehran Iran Department of Health Management and Economics Tehran University of Medical Sciences Tehran Iran Department of Microbiology Tehran University of Medical Sciences Tehran Iran Department of Pharmacology Tehran University of Medical Sciences Tehran Iran Digestive Diseases Research Institute Tehran University of Medical Sciences Tehran Iran Endocrinology and Metabolism Research Center Tehran University of Medical Sciences Tehran Iran Hematology-Oncology and Stem Cell Transplantation Research Center Tehran University of Medical Sciences Tehran Iran Iran National Institute of Health Research Tehran University of Medical Sciences Tehran Iran Metabolomics and

Summary Background Across low-income and middle-income countries (LMICs), one in ten deaths in children younger than 5 years is attributable to diarrhoea. The substantial between-country variation in both diarrhoea incidence and mortality is attributable to interventions that protect children, prevent infection, and treat disease. Identifying subnational regions with the highest burden and mapping associated risk factors can aid in reducing preventable childhood *** We used Bayesian model-based geostatistics and a geolocated dataset comprising 15 072 746 children younger than 5 years from 466 surveys in 94 LMICs, in combination with findings of the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2017, to estimate posterior distributions of diarrhoea prevalence, incidence, and mortality from 2000 to 2017. From these data, we estimated the burden of diarrhoea at varying subnational levels (termed units) by spatially aggregating draws, and we investigated the drivers of subnational patterns by creating aggregated risk factor *** The greatest declines in diarrhoeal mortality were seen in south and southeast Asia and South America, where 54·0% (95% uncertainty interval [UI] 38·1-65·8), 17·4% (7·7-28·4), and 59·5% (34·2-86·9) of units, respectively, recorded decreases in deaths from diarrhoea greater than 10%. Although children in much of Africa remain at high risk of death due to diarrhoea, regions with the most deaths were outside Africa, with the highest mortality units located in Pakistan. Indonesia showed the greatest within-country geographical inequality; some regions had mortality rates nearly four times the average country rate. Reductions in mortality were correlated to improvements in water, sanitation, and hygiene (WASH) or reductions in child growth failure (CGF). Similarly, most high-risk areas had poor WASH, high CGF, or low oral rehydration therapy *** By co-analysing geospatial trends in d

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving tag transfer for image annotation using visual and semantic information

Improving tag transfer for image annotation using visual and...

引用

International Workshop on Content-Based Multimedia Indexing, CBMI

作者： Sergio Rodriguez-Vaamonde Lorenzo Torresani Koldo Espinosa Estibaliz Garrote Computer Vision Area-ICT/ESI Division TECNALIA Zamudio Spain Visual-Learning Group-CS Department Dartmouth College Hanover USA Multimedia Group-Communications Engineering Department University of the Basque Country Bilbao Spain

This paper addresses the problem of image annotation using a combination of visual and semantic information. Our model involves two stages: a Nearest Neighbor computation and a tag transfer stage that collects the final annotations. For the latter stage, several algorithms have been implemented in the past using labels' information or including implicitly some visual features. In this paper we propose a novel algorithm for tag transfer that takes advantage explicitly of semantic and visual information. We also present a structured training procedure based on a concept we have called Image Networking: all the images in a training database are “connected” visually and semantically, so it is possible to exploit these connections to learn the tag transfer parameters at annotation time. This learning is local for the test image and it exploits the information obtained in the Nearest Neighbor computation stage. We demonstrate that our approach achieves state-of-the-art performance on the ImageCLEF2011 dataset.

关键词： Visualization Training Semantics Databases Image color analysis Image edge detection Vectors

来源：评论

学校读者我要写书评

暂无评论

26th Annual Computational Neuroscience Meeting (CNS*2017): Part 3 Antwerp, Belgium. 15-20 July 2017 Abstracts

引用

BMC NEUROSCIENCE 2017年第SUPPL 1期18卷 95-176页

作者： [Anonymous] Department of Neuroscience Yale University New Haven CT 06520 USA Department Physiology & Pharmacology SUNY Downstate Brooklyn NY 11203 USA NYU School of Engineering 6 MetroTech Center Brooklyn NY 11201 USA Departament de Matemàtica Aplicada Universitat Politècnica de Catalunya Barcelona 08028 Spain Institut de Neurobiologie de la Méditerrannée (INMED) INSERM UMR901 Aix-Marseille Univ Marseille France Center of Neural Science New York University New York NY USA Aix-Marseille Univ INSERM INS Inst Neurosci Syst Marseille France Laboratoire de Physique Théorique et Modélisation CNRS UMR 8089 Université de Cergy-Pontoise 95300 Cergy-Pontoise Cedex France Department of Mathematics and Computer Science ENSAT Abdelmalek Essaadi’s University Tangier Morocco Laboratory of Natural Computation Department of Information and Electrical Engineering and Applied Mathematics University of Salerno 84084 Fisciano SA Italy Department of Medicine University of Salerno 84083 Lancusi SA Italy Dipartimento di Fisica Università degli Studi Aldo Moro Bari and INFN Sezione Di Bari Italy Data Analysis Department Ghent University Ghent Belgium Coma Science Group University of Liège Liège Belgium Cruces Hospital and Ikerbasque Research Center Bilbao Spain BIOtech Department of Industrial Engineering University of Trento and IRCS-PAT FBK 38010 Trento Italy Department of Data Analysis Ghent University Ghent 9000 Belgium The Wellcome Trust Centre for Neuroimaging University College London London WC1N 3BG UK Department of Electronic Engineering NED University of Engineering and Technology Karachi Pakistan Blue Brain Project École Polytechnique Fédérale de Lausanne Lausanne Switzerland Departement of Mathematics Swansea University Swansea Wales UK Laboratory for Topology and Neuroscience at the Brain Mind Institute École polytechnique fédérale de Lausanne Lausanne Switzerland Institute of Mathematics University of Aberdeen Aberdeen Scotland UK Department of Integrativ

来源：评论

学校读者我要写书评

暂无评论

LETHA: learning from High Quality Inputs for 3D Pose Estimation in Low Quality Images

LETHA: Learning from High Quality Inputs for 3D Pose Estimat...

引用

International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)

作者： Adrian Penate-Sanchez Francesc Moreno-Noguer Juan Andrade-Cetto François Fleuret Institut de Robòtica i Informàtica Industrial CSIC-UPC Barcelona Spain Computer Vision and Learning group Idiap research institute Martigny Switzerland Ecole Poly technique Federale de Lausanne Lausanne Switzerland

We introduce LETHA (learning on Easy data, Test on Hard), a new learning paradigm consisting of building strong priors from high quality training data, and combining them with discriminative machine learning to deal with low-quality test data. Our main contribution is an implementation of that concept for pose estimation. We first automatically build a 3D model of the object of interest from high-definition images, and devise from it a pose-indexed feature extraction scheme. We then train a single classifier to process these feature vectors. Given a low quality test image, we visit many hypothetical poses, extract features consistently and evaluate the response of the classifier. Since this process uses locations recorded during learning, it does not require matching points anymore. We use a boosting procedure to train this classifier common to all poses, which is able to deal with missing features, due in this context to self-occlusion. Our results demonstrate that the method combines the strengths of global image representations, discriminative even for very tiny images, and the robustness to occlusions of approaches based on local feature point descriptors.

关键词： Training Three-dimensional displays Feature extraction Vectors Solid modeling Estimation Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Adaptive sampling for large scale boosting

The Journal of Machine Learning Research

引用

The Journal of Machine learning Research 2014年第1期15卷

作者： Kevin Murphy Bernhard Schölkopf Charles Dubout François Fleuret Google Computer Vision and Learning Group Idiap Research Institute Martigny Switzerland

Classical boosting algorithms, such as AdaBoost, build a strong classifier without concern for the computational cost. Some applications, in particular in computer vision, may involve millions of training examples and very large feature spaces. In such contexts, the training time of off-the-shelf boosting algorithms may become prohibitive. Several methods exist to accelerate training, typically either by sampling the features or the examples used to train the weak learners. Even if some of these methods provide a guaranteed speed improvement, they offer no insurance of being more efficient than any other, given the same amount of *** contributions of this paper are twofold: (1) a strategy to better deal with the increasingly common case where features come from multiple sources (for example, color, shape, texture, etc., in the case of images) and therefore can be partitioned into meaningful subsets; (2) new algorithms which balance at every boosting iteration the number of weak learners and the number of training examples to look at in order to maximize the expected loss reduction. Experiments in image classification and object recognition on four standard computer vision data sets show that the adaptive methods we propose outperform basic sampling and state-of-the-art bandit methods.

关键词： boosting feature selection large scale learning

来源：评论

学校读者我要写书评

暂无评论

25th Annual Computational Neuroscience Meeting CNS-2016, Seogwipo City, South Korea, July 2-7, 2016 Abstracts

引用

BMC NEUROSCIENCE 2016年第1期17卷 1-112页

作者： [Anonymous] Computational Neurobiology Laboratory The Salk Institute for Biological Studies San Diego USA UNIC CNRS Gif sur Yvette France The European Institute for Theoretical Neuroscience (EITN) Paris France ATR Computational Neuroscience Laboratories Kyoto Japan Krembil Research Institute University Health Network Toronto Canada Department of Physiology University of Toronto Toronto Canada Department of Medicine (Neurology) University of Toronto Toronto Canada Department of Physics University of New Hampshire Durham USA Department of Neurophysiology Nencki Institute of Experimental Biology Warsaw Poland Department of Theory Wigner Research Centre for Physics of the Hungarian Academy of Sciences Budapest Hungary Department of Mathematical Sciences KAIST Daejoen Republic of Korea Department of Mathematics University of Houston Houston USA Department of Biochemistry & Cell Biology and Institute of Biosciences and Bioengineering Rice University Houston USA Department of Biology and Biochemistry University of Houston Houston USA Grupo de Neurocomputación Biológica Dpto. de Ingeniería Informática Escuela Politécnica Superior Universidad Autónoma de Madrid Madrid Spain Department of Biological Sciences University of Southern California Los Angeles USA Center for Neuroscience Korea Institute of Science and Technology Seoul South Korea Department of Neurology Albert Einstein College of Medicine Bronx USA Center for Neuroscience KIST Seoul South Korea Department of Neuroscience University of Science and Technology Daejon South Korea Systems Neuroscience Group QIMR Berghofer Medical Research Institute Herston Australia Department of Psychology Yonsei University Seoul South Korea Department of Psychiatry Kyung Hee University Hospital at Gangdong Seoul South Korea Department of Psychiatry Veterans Administration Boston Healthcare System and Harvard Medical School Brockton USA Department of Electrical and Electronic Engineering The University of Melbourne Parkvil

A1 Functional advantages of cell-type heterogeneity in neural circuits Tatyana O. Sharpee A2 Mesoscopic modeling of propagating waves in visual cortex Alain Destexhe A3 Dynamics and biomarkers of mental disorders Mitsuo Kawato F1 Precise recruitment of spiking output at theta frequencies requires dendritic h-channels in multi-compartment models of oriens-lacunosum/moleculare hippocampal interneurons Vladislav Sekulić, Frances K. Skinner F2 Kernel methods in reconstruction of current sources from extracellular potentials for single cells and the whole brains Daniel K. Wójcik, Chaitanya Chintaluri, Dorottya Cserpán, Zoltán Somogyvári F3 The synchronized periods depend on intracellular transcriptional repression mechanisms in circadian clocks. Jae Kyoung Kim, Zachary P. Kilpatrick, Matthew R. Bennett, Kresimir Josić O1 Assessing irregularity and coordination of spiking-bursting rhythms in central pattern generators Irene Elices, David Arroyo, Rafael Levi, Francisco B. Rodriguez, Pablo Varona O2 Regulation of top-down processing by cortically-projecting parvalbumin positive neurons in basal forebrain Eunjin Hwang, Bowon Kim, Hio-Been Han, Tae Kim, James T. McKenna, Ritchie E. Brown, Robert W. McCarley, Jee Hyun Choi O3 Modeling auditory stream segregation, build-up and bistability James Rankin, Pamela Osborn Popp, John Rinzel O4 Strong competition between tonotopic neural ensembles explains pitch-related dynamics of auditory cortex evoked fields Alejandro Tabas, André Rupp, Emili Balaguer-Ballester O5 A simple model of retinal response to multi-electrode stimulation Matias I. Maturana, David B. Grayden, Shaun L. Cloherty, Tatiana Kameneva, Michael R. Ibbotson, Hamish Meffin O6 Noise correlations in V4 area correlate with behavioral performance in visual discrimination task Veronika Koren, Timm Lochmann, Valentin Dragoi, Klaus Obermayer O7 Input-location dependent gain modulation in cerebellar nucleus neurons Maria Psarrou, Maria Schilstra, Neil Davey, Benjamin Torben-Ni

关键词：

来源：评论

学校读者我要写书评

暂无评论

Brain tumor cell density estimation from multi-modal MR images based on a synthetic tumor growth model

Brain tumor cell density estimation from multi-modal MR imag...

引用

15th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2012

作者： Geremia, Ezequiel Menze, Bjoern H. Prastawa, Marcel Weber, M.-A. Criminisi, Antonio Ayache, Nicholas Asclepios Research Project INRIA Sophia-Antipolis France Computer Science and Artificial Intelligence Laboratory MIT United States Computer Vision Laboratory ETH Zurich Switzerland Scientific Computing and Imaging Institute University of Utah United States Diagnostic and Interventional Radiology Heidelberg University Hospital Germany Machine Learning and Perception Group Microsoft Research Cambridge United Kingdom

ISBN: (纸本)9783642366192

This paper proposes to employ a detailed tumor growth model to synthesize labelled images which can then be used to train an efficient data-driven machine learning tumor predictor. Our MR image synthesis step generates images with both healthy tissues as well as various tumoral tissue types. Subsequently, a discriminative algorithm based on random regression forests is trained on the simulated ground truth to predict the continuous latent tumor cell density, and the discrete tissue class associated with each voxel. The presented method makes use of a large synthetic dataset of 740 simulated cases for training and evaluation. A quantitative evaluation on 14 real clinical cases diagnosed with low-grade gliomas demonstrates tissue class accuracy comparable with state of the art, with added benefit in terms of computational efficiency and the ability to estimate tumor cell density as a latent variable underlying the multimodal image observations. The idea of synthesizing training data to train data-driven learning algorithms can be extended to other applications where expert annotation is lacking or expensive. © 2013 Springer-Verlag.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：