arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.01668cs.LGcs.CVstat.ML
收藏

分段线性动力系统的变分推理与学习

Variational Inference and Learning of Piecewise-linear Dynamical Systems

INRIA Grenoble Rhône-Alpes(法国国家信息与自动化研究所格勒诺布尔-罗纳-阿尔卑斯分部);Image Metrics(图像度量公司)

Xavier Alameda-Pineda, Vincent Drouard, Radu Horaud

摘要:

在许多科学和工程领域中,对数据的时态行为进行建模是至关重要的。基线方法假定动态方程和观测方程都遵循线性高斯模型。然而,现实世界中有许多过程不能用单一的线性行为来表征。或者,可以考虑分段线性模型,该模型与切换机制相结合,当需要几种行为模式时非常适合。然而,切换动力系统是棘手的,因为它们的计算复杂性随时间呈指数增长。本文提出了分段线性动力系统的一种变分逼近。我们提供了完整的细节,推导出两个变分期望最大化算法,过滤器和平滑。我们表明,模型参数可以分为两组,静态和动态参数,和前参数可以估计离线连同线性模式的数量,或状态的开关变量的数量。我们将所提出的方法应用于视觉跟踪问题,即头部姿态跟踪,我们彻底比较我们的算法与几个国家的最先进的跟踪器。

英文摘要:

Modeling the temporal behavior of data is of primordial importance in many scientific and engineering fields. Baseline methods assume that both the dynamic and observation equations follow linear-Gaussian models. However, there are many real-world processes that cannot be characterized by a single linear behavior. Alternatively, it is possible to consider a piecewise-linear model which, combined with a switching mechanism, is well suited when several modes of behavior are needed. Nevertheless, switching dynamical systems are intractable because of their computational complexity increases exponentially with time. In this paper, we propose a variational approximation of piecewise linear dynamical systems. We provide full details of the derivation of two variational expectation-maximization algorithms, a filter and a smoother. We show that the model parameters can be split into two sets, static and dynamic parameters, and that the former parameters can be estimated off-line together with the number of linear modes, or the number of states of the switching variable. We apply the proposed method to a visual tracking problem, namely head-pose tracking, and we thoroughly compare our algorithm with several state of the art trackers.

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。

↑