检索结果-内蒙古大学图书馆

Annual Conference on Neural Information Processing Systems

作者： Hamed Masnadi-Shirazi Nuno Vasconcelos Statistical Visual Computing Laboratory University of California San Diego LaJollaCA 92039

ISBN: (纸本)9781617823800

The problem of controlling the margin of a classifier is studied. A detailed analytical study is presented on how properties of the classification risk, such as its optimal link and minimum risk functions, are related to the shape of the loss, and its margin enforcing properties. It is shown that for a class of risks, denoted canonical risks, asymptotic Bayes consistency is compatible with simple analytical relationships between these functions. These enable a precise characterization of the loss for a popular class of link functions. It is shown that, when the risk is in canonical form and the link is inverse sigmoidal, the margin properties of the loss are determined by a single parameter. Novel families of Bayes consistent loss functions, of variable margin, are derived. These families are then used to design boosting style algorithms with explicit control of the classification margin. The new algorithms generalize well established approaches, such as LogitBoost. Experimental results show that the proposed variable margin losses outperform the fixed margin counterparts used by existing algorithms. Finally, it is shown that best performance can be achieved by cross-validating the margin parameter.

关键词： Tumor margin status Classifiers Canonical form Variable

来源：评论

学校读者我要写书评

暂无评论

On the design of loss functions for classification: theory, robustness to outliers, and SavageBoost 08

On the design of loss functions for classification: theory, ...

引用

Proceedings of the 22nd International Conference on Neural Information Processing Systems

作者： Hamed Masnadi-Shirazi Nuno Vasconcelos Statistical Visual Computing Laboratory University of California San Diego La Jolla CA

ISBN: (纸本)9781605609492

The machine learning problem of classifier design is studied from the perspective of probability elicitation, in statistics. This shows that the standard approach of proceeding from the specification of a loss, to the minimization of conditional risk is overly restrictive. It is shown that a better alternative is to start from the specification of a functional form for the minimum conditional risk, and derive the loss function. This has various consequences of practical interest, such as showing that 1) the widely adopted practice of relying on convex loss functions is unnecessary, and 2) many new losses can be derived for classification problems. These points are illustrated by the derivation of a new loss which is not convex, but does not compromise the computational tractability of classifier design, and is robust to the contamination of data with outliers. A new boosting algorithm, SavageBoost, is derived for the minimization of this loss. Experimental results show that it is indeed less sensitive to outliers than conventional methods, such as Ada, Real, or LogitBoost, and converges in fewer iterations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boosting Classifier Cascades 10

Boosting Classifier Cascades

引用

Annual Conference on Neural Information Processing Systems

作者： Mohammad J. Saberian Nuno Vasconcelos Statistical Visual Computing Laboratory University of California San Diego La Jolla CA 92039

ISBN: (纸本)9781617823800

The problem of optimal and automatic design of a detector cascade is considered. A novel mathematical model is introduced for a cascaded detector. This model is analytically tractable, leads to recursive computation, and accounts for both classification and complexity. A boosting algorithm, FCBoost, is proposed for fully automated cascade design. It exploits the new cascade model, minimizes a La-grangian cost that accounts for both classification risk and complexity. It searches the space of cascade configurations to automatically determine the optimal number of stages and their predictors, and is compatible with bootstrapping of negative examples and cost sensitive learning. Experiments show that the resulting cascades have state-of-the-art performance in various computer vision problems.

关键词： optimum number computer vision waterfalls Computer-Aided Design Boost bootstrapping cascade configuration Classifiers Optimal

来源：评论

学校读者我要写书评

暂无评论

A biologically plausible network for the computation of orientation dominance 10

A biologically plausible network for the computation of orie...

引用

Annual Conference on Neural Information Processing Systems

作者： Kritika Muralidharan Nuno Vasconcelos Statistical Visual Computing Laboratory University of California San Diego La Jolla CA 92039

ISBN: (纸本)9781617823800

The determination of dominant orientation at a given image location is formulated as a decision-theoretic question. This leads to a novel measure for the dominance of a given orientation 9, which is similar to that used by SIFT. It is then shown that the new measure can be computed with a network that implements the sequence of operations of the standard neurophysiological model of V1. The measure can thus be seen as a biologically plausible version of SIFT, and is denoted as bioSIFT. The network units are shown to exhibit trademark properties of VI neurons, such as cross-orientation suppression, sparseness and independence. The connection between SIFT and biological vision provides a justification for the success of SIFT-like features and reinforces the importance of contrast normalization in computer vision. We illustrate this by replacing the Gabor units of an HMAX network with the new bioSIFT units. This is shown to lead to significant gains for classification tasks, leading to state-of-the-art performance among biologically inspired network models and performance competitive with the best non-biological object recognition systems.

关键词： Sifting network model dominance Reasoning computer vision Network

来源：评论

学校读者我要写书评

暂无评论

Scalable discriminant feature selection for image retrieval and recognition

Scalable discriminant feature selection for image retrieval ...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： N. Vasconcelos M. Vasconcelos Statistical Visual Computing Laboratory University of California San Diego USA Harvard Robotics Laboratory Harvard University USA

Problems such as object recognition or image retrieval require feature selection (FS) algorithms that scale well enough to be applicable to databases containing large numbers of image classes and large amounts of data per class. We exploit recent connections between information theoretic feature selection and minimum Bayes error solutions to derive FS algorithms that are optimal in a discriminant sense without compromising scalability. We start by formalizing the intuition that optimal FS must favor discriminant features while penalizing discriminant features that are redundant. We then rely on this result to derive a new family of FS algorithms that enables an explicit trade-off between complexity and classification optimality. This trade-off is controlled by a parameter that encodes the order of feature redundancies that must be explicitly modeled to achieve the optimal solution. Experimental results on databases of natural images show that this order is usually low, enabling optimal FS with very low complexity.

关键词： Image retrieval Image recognition Scalability Laboratories Information retrieval Image databases Spatial databases Face detection Large-scale systems Biology computing

来源：评论

学校读者我要写书评

暂无评论

On the connections between saliency and tracking 12

On the connections between saliency and tracking

引用

Annual Conference on Neural Information Processing Systems

作者： Vijay Mahadevan Nuno Vasconcelos Yahoo! Labs Bangalore India Statistical Visual Computing Laboratory UC San Diego La Jolla CA 92092

ISBN: (纸本)9781627480031

A model connecting visual tracking and saliency has recently been proposed. This model is based on the saliency hypothesis for tracking which postulates that tracking is achieved by the top-down tuning, based on target features, of discriminant center-surround saliency mechanisms over time. In this work, we identify three main predictions that must hold if the hypothesis were true: 1) tracking reliability should be larger for salient than for non-salient targets, 2) tracking reliability should have a dependence on the defining variables of saliency, namely feature contrast and distractor heterogeneity, and must replicate the dependence of saliency on these variables, and 3) saliency and tracking can be implemented with common low level neural mechanisms. We confirm that the first two predictions hold by reporting results from a set of human behavior studies on the connection between saliency and tracking. We also show that the third prediction holds by constructing a common neurophysiologically plausible architecture that can computationally solve both saliency and tracking. This architecture is fully compliant with the standard physiological models of VI and MT, and with what is known about attentional control in area LIP, while explaining the results of the human behavior experiments.

关键词： tracking Connections Human behavior visual tracking

来源：评论

学校读者我要写书评

暂无评论

Boosting algorithms for detector cascade learning

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 Mohammad Saberian Nuno Vasconcelos Google Statistical Visual Computing Laboratory University of California San Diego La Jolla CA

The problem of learning classifier cascades is considered. A new cascade boosting algorithm, fast cascade boosting (FCBoost), is proposed. FCBoost is shown to have a number of interesting properties, namely that it 1) minimizes a Lagrangian risk that jointly accounts for classification accuracy and speed, 2) generalizes adaboost, 3) can be made cost-sensitive to support the design of high detection rate cascades, and 4) is compatible with many predictor structures suitable for sequential decision making. It is shown that a rich family of such structures can be derived recursively from cascade predictors of two stages, denoted cascade generators. Generators are then proposed for two new cascade families, last-stage and multiplicative cascades, that generalize the two most popular cascade architectures in the literature. The concept of neutral predictors is finally introduced, enabling FCBoost to automatically determine the cascade configuration, i.e., number of stages and number of weak learners per stage, for the learned cascades. Experiments on face and pedestrian detection show that the resulting cascades outperform current state-of-the-art methods in both detection accuracy and speed.

关键词： boosting complexity-constrained learning cost-sensitive learning detector cascades ensemble methods real-time object detection sequential decision-making

来源：评论

学校读者我要写书评

暂无评论

A view of margin losses as regularizers of probability estimates

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2015年第1期16卷

作者： Hamed Masnadi-Shirazi Nuno Vasconcelos School of Electrical and Computer Engineering Shiraz University Shiraz Iran Statistical Visual Computing Laboratory University of California San Diego La Jolla CA

Regularization is commonly used in classifier design, to assure good generalization. Classical regularization enforces a cost on classifier complexity, by constraining parameters. This is usually combined with a margin loss, which favors large-margin decision rules. A novel and unified view of this architecture is proposed, by showing that margin losses act as regularizers of posterior class probabilities, in a way that amplifies classical parameter regularization. The problem of controlling the regularization strength of a margin loss is considered, using a decomposition of the loss in terms of a link and a binding function. The link function is shown to be responsible for the regularization strength of the loss, while the binding function determines its outlier robustness. A large class of losses is then categorized into equivalence classes of identical regularization strength or outlier robustness. It is shown that losses in the same regularization class can be parameterized so as to have tunable regularization strength. This parameterization is finally used to derive boosting algorithms with loss regularization (BoostLR). Three classes of tunable regularization losses are considered in detail. Canonical losses can implement all regularization behaviors but have no flexibility in terms of outlier modeling. Shrinkage losses support equally parameterized link and binding functions, leading to boosting algorithms that implement the popular shrinkage procedure. This offers a new explanation for shrinkage as a special case of loss-based regularization. Finally, α-tunable losses enable the independent parameterization of link and binding functions, leading to boosting algorithms of great exibility. This is illustrated by the derivation of an algorithm that generalizes both AdaBoost and LogitBoost, behaving as either one when that best suits the data to classify. Various experiments provide evidence of the benefits of probability regularization for both classification a

关键词： binding functions boosting classification generalization link functions loss functions margin losses probability elicitation regularization shrinkage

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

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：