For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Stochastic Dykstra Algorithms for Distance Metric Learning with Covariance Descriptors
Tomoki MATSUZAWA Eisuke ITO Raissa RELATOR Jun SESE Tsuyoshi KATO
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2017/04/01
Online ISSN: 1745-1361
Type of Manuscript: PAPER
Category: Pattern Recognition
covariance descriptor, metric learning, convex optimization, stochastic optimization, Dykstra algorithm,
Full Text: PDF(554.3KB)
>>Buy this Article
In recent years, covariance descriptors have received considerable attention as a strong representation of a set of points. In this research, we propose a new metric learning algorithm for covariance descriptors based on the Dykstra algorithm, in which the current solution is projected onto a half-space at each iteration, and which runs in O(n3) time. We empirically demonstrate that randomizing the order of half-spaces in the proposed Dykstra-based algorithm significantly accelerates convergence to the optimal solution. Furthermore, we show that the proposed approach yields promising experimental results for pattern recognition tasks.