arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.04889cs.LGeess.SP
收藏

基于亲和度的相关概念分层学习在人体活动识别中的应用

Affinity-Based Hierarchical Learning of Dependent Concepts for Human Activity Recognition

LIPN-UMR CNRS 7030, Univ. Sorbonne Paris Nord(巴黎第十三大学(索邦巴黎北部大学)LIPN-UMR CNRS 7030实验室);Léonard de Vinci Pôle Universitaire, Research Center(达芬奇大学联盟研究中心)

Aomar Osmani, Massinissa Hamidi, Pegah Alizadeh

摘要:

在多类分类任务中,如人类活动识别,通常假设类是可分离的。在实际应用中,这种假设变得很强,并产生不一致性。此外,最常用的方法是一个接一个地学习其他课程。这种计算简化原则在学习理论上引入了强烈的归纳偏见。事实上,某些阶级之间的自然联系,而不是其他阶级之间的自然联系,值得考虑。在本文中,我们表明,组织重叠的类(多个继承)到层次结构大大提高了分类性能。在SHL数据集中的活动识别任务中尤其如此。在理论上表明可能的类层次结构的指数复杂性后,我们提出了一种基于类之间的转移亲和力来确定学习过程的最佳层次结构的方法。大量的实验表明,改进的性能和减少需要学习的例子的数量。

英文摘要:

In multi-class classification tasks, like human activity recognition, it is often assumed that classes are separable. In real applications, this assumption becomes strong and generates inconsistencies. Besides, the most commonly used approach is to learn classes one-by-one against the others. This computational simplification principle introduces strong inductive biases on the learned theories. In fact, the natural connections among some classes, and not others, deserve to be taken into account. In this paper, we show that the organization of overlapping classes (multiple inheritances) into hierarchies considerably improves classification performances. This is particularly true in the case of activity recognition tasks featured in the SHL dataset. After theoretically showing the exponential complexity of possible class hierarchies, we propose an approach based on transfer affinity among the classes to determine an optimal hierarchy for the learning process. Extensive experiments show improved performances and a reduction in the number of examples needed to learn.

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。

↑