Efficient Computation of Robust Low-Rank Matrix Approxi.pptVIP

在真实数据上的实验结果 QA Thank you! Efficient Computation of Robust Low-Rank Matrix Approximations in the Presence of Missing Data using the L1 Norm * university of adelaide　 阿德雷德大学 * 阿达马乘积 克罗克内积 * * * * * * * * * A plot showing the convergence rate of the alternated quadratic programming and L1-Wiberg algorithms over 100 trials. The error are presented on a logarithmic scale. [Log Error vs. Iteration] * Efficient Computation of Robust Low-Rank Matrix Approximations in the Presence of Missing Data using the L1 Norm Jing Chen 2010.12.31 文章信息 标题 Efficient Computation of Robust Low-Rank Matrix Approximations in the Presence of Missing Data using the L1 Norm 出处 CVPR，2010 作者信息 Anders Eriksson 阿德雷德大学计算机科学系 Anton van den Hengel 职位 Director ：The Australian Centre for Visual Technologies Professor ：CS, The University of Adelaide 研究领域 Video Trace, Rapid interactive scene modeling from video Constrained Generalized Principal Component Analysis Parameter Estimation Camera calibration and ego-motion determination from image sequences (structure from motion) Space carving 文章发表情况 TIP’07, TOG’07… Abstract The calculation of a low-rank approximation of a matrix is a fundamental operation in many computer vision applications. The workhorse of this class of problems has long been the Singular Value Decomposition. However, in the presence of missing data and outliers this method is not applicable, and unfortunately, this is often the case in practice. In this paper we present a method for calculating the low-rank factorization of a matrix which minimizes the L1 norm in the presence of missing data. Our approach represents a generalization the Wiberg algorithm of one of the more convincing methods for factorization under the L2 norm. By utilizing the differentiability of linear programs, we can extend the underlying ideas behind this approach to include this class of L1 problems as well. We show that the proposed algorithm can be efficiently implemented using existing optimiz