arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.05947cs.CV
收藏

时间Transformer网络:不变性和判别性时间规整的联合学习

Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping

Arizona State University(亚利桑那州立大学)

Suhas Lohit, Qiao Wang, Pavan Turaga

摘要:

许多时间序列分类问题涉及开发对时间错位不变的度量。在人体活动分析中,由于各种原因,包括不同的初始相位,传感器采样率,和弹性时间扭曲,由于受试者特定的生物力学的时间错位出现。过去在这方面的工作只着眼于通过弹性时间对齐来减少类内变异。在本文中,我们提出了一种基于模型和数据驱动的混合方法来学习扭曲函数,不仅减少了类内变异,而且增加了类间分离。我们称之为时间Transformer网络(TTN)。TTN是一个可解释的可微分模块,可以很容易地集成在分类网络的前端。该模块能够通过生成导致速率鲁棒表示的依赖于输入的扭曲函数来减少类内方差。同时,它通过学习更具区分力的扭曲函数来增加类间方差。我们使用所提出的框架在具有挑战性的数据集上的3D动作识别中显示了强基线的改进。当训练集较小时,这种改进尤其明显。

英文摘要:

Many time-series classification problems involve developing metrics that are invariant to temporal misalignment. In human activity analysis, temporal misalignment arises due to various reasons including differing initial phase, sensor sampling rates, and elastic time-warps due to subject-specific biomechanics. Past work in this area has only looked at reducing intra-class variability by elastic temporal alignment. In this paper, we propose a hybrid model-based and data-driven approach to learn warping functions that not just reduce intra-class variability, but also increase inter-class separation. We call this a temporal transformer network (TTN). TTN is an interpretable differentiable module, which can be easily integrated at the front end of a classification network. The module is capable of reducing intra-class variance by generating input-dependent warping functions which lead to rate-robust representations. At the same time, it increases inter-class variance by learning warping functions that are more discriminative. We show improvements over strong baselines in 3D action recognition on challenging datasets using the proposed framework. The improvements are especially pronounced when training sets are smaller.

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。

↑