Proceedings. IEEE International Conference on Computer Vision最新文献_第4页

Metric Learning Using Iwasawa Decomposition. 使用Iwasawa分解的度量学习。

Proceedings. IEEE International Conference on Computer Vision Pub Date : 2007-10-01 DOI: 10.1109/ICCV.2007.4408846

Bing Jian, Baba C Vemuri

{"title":"Metric Learning Using Iwasawa Decomposition.","authors":"Bing Jian, Baba C Vemuri","doi":"10.1109/ICCV.2007.4408846","DOIUrl":"10.1109/ICCV.2007.4408846","url":null,"abstract":"Finding a good metric over the input space plays a fundamental role in machine learning. Most existing techniques use the Mahalanobis metric without incorporating the geometry of positive matrices and experience difficulties in the optimization procedure. In this paper we introduce the use of Iwasawa decomposition, a unique and effective parametrization of symmetric positive definite (SPD) matrices, for performing metric learning tasks. Unlike other previously employed factorizations, the use of the Iwasawa decomposition is able to reformulate the semidefinite programming (SDP) problems as smooth convex nonlinear programming (NLP) problems with much simpler constraints. We also introduce a modified Iwasawa coordinates for rank-deficient positive semidefinite (PSD) matrices which enables the unifying of the metric learning and linear dimensionality reduction. We show that the Iwasawa decomposition can be easily used in most recent proposed metric learning algorithms and have applied it to the Neighbourhood Components Analysis (NCA). The experimental results on several public domain datasets are also presented.","PeriodicalId":74564,"journal":{"name":"Proceedings. IEEE International Conference on Computer Vision","volume":"2007 Article 4408846","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2630184/pdf/nihms73487.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"27949054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Locally-Constrained Region-Based Methods for DW-MRI Segmentation. 基于局部约束区域的DW-MRI分割方法。

Proceedings. IEEE International Conference on Computer Vision Pub Date : 2007-01-01 DOI: 10.1109/iccv.2007.4409167

John Melonakos, Marc Niethammer, Vandana Mohan, Marek Kubicki, James V Miller, Allen Tannenbaum

引用次数: 15

Diffusion Tensor Estimation by Maximizing Rician Likelihood. 最大似然扩散张量估计。

Proceedings. IEEE International Conference on Computer Vision Pub Date : 2007-01-01 DOI: 10.1109/iccv.2007.4409140

Bennett Landman, Pierre-Louis Bazin, Jerry Prince

{"title":"Diffusion Tensor Estimation by Maximizing Rician Likelihood.","authors":"Bennett Landman, Pierre-Louis Bazin, Jerry Prince","doi":"10.1109/iccv.2007.4409140","DOIUrl":"10.1109/iccv.2007.4409140","url":null,"abstract":"Diffusion tensor imaging (DTI) is widely used to characterize white matter in health and disease. Previous approaches to the estimation of diffusion tensors have either been statistically suboptimal or have used Gaussian approximations of the underlying noise structure, which is Rician in reality. This can cause quantities derived from these tensors - e.g., fractional anisotropy and apparent diffusion coefficient - to diverge from their true values, potentially leading to artifactual changes that confound clinically significant ones. This paper presents a novel maximum likelihood approach to tensor estimation, denoted Diffusion Tensor Estimation by Maximizing Rician Likelihood (DTEMRL). In contrast to previous approaches, DTEMRL considers the joint distribution of all observed data in the context of an augmented tensor model to account for variable levels of Rician noise. To improve numeric stability and prevent non-physical solutions, DTEMRL incorporates a robust characterization of positive definite tensors and a new estimator of underlying noise variance. In simulated and clinical data, mean squared error metrics show consistent and significant improvements from low clinical SNR to high SNR. DTEMRL may be readily supplemented with spatial regularization or a priori tensor distributions for Bayesian tensor estimation.","PeriodicalId":74564,"journal":{"name":"Proceedings. IEEE International Conference on Computer Vision","volume":" ","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2007-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3488430/pdf/nihms357234.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"31033866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Robust Algorithm for Point Set Registration Using Mixture of Gaussians. 一种基于混合高斯的点集配准鲁棒算法。

Proceedings. IEEE International Conference on Computer Vision Pub Date : 2005-10-01 DOI: 10.1109/ICCV.2005.17

Bing Jian, Baba C Vemuri

引用次数: 0