arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.14272cs.LGstat.ML
收藏

对称半正定黎曼几何及其在领域自适应中的应用

Symmetric Positive Semi-definite Riemannian Geometry with Application to Domain Adaptation

Technion, Israel Institute of Technology(以色列理工学院)

Or Yair, Almog Lahav, Ronen Talmon

摘要:

本文给出了对称半正定(SPSD)矩阵的黎曼几何的新结果。首先,基于现有的近似的测地线路径,我们介绍了对数和指数映射的近似。其次,我们提出了一个封闭形式的表达并行传输(PT)。第三,我们推导出一组SPSD矩阵的规范表示。基于这些结果,我们提出了一个算法的领域自适应(DA),并证明其性能在两个应用:高光谱图像融合和运动识别。

英文摘要:

In this paper, we present new results on the Riemannian geometry of symmetric positive semi-definite (SPSD) matrices. First, based on an existing approximation of the geodesic path, we introduce approximations of the logarithmic and exponential maps. Second, we present a closed-form expression for Parallel Transport (PT). Third, we derive a canonical representation for a set of SPSD matrices. Based on these results, we propose an algorithm for Domain Adaptation (DA) and demonstrate its performance in two applications: fusion of hyper-spectral images and motion identification.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑