For time series classification task using 1D-CNN, the selection of kernel size is critically important to ensure the model can capture the right scale salient signal from a long time-series. Most of the existing work on 1D-CNN treats the kernel size as a hyper-parameter and tries to find the proper kernel size through a grid search which is time-consuming and is inefficient. This paper theoretically analyses how kernel size impacts the performance of 1D-CNN. Considering the importance of kernel size, we propose a novel Omni-Scale 1D-CNN (OS-CNN) architecture to capture the proper kernel size during the model learning period. A specific design for kernel size configuration is developed which enables us to assemble very few kernel-size options to represent more receptive fields. The proposed OS-CNN method is evaluated using the UCR archive with 85 datasets. The experiment results demonstrate that our method is a stronger baseline in multiple performance indicators, including the critical difference diagram, counts of wins, and average accuracy. We also published the experimental source codes at GitHub (https://github.com/Wensi-Tang/OS-CNN/).

本文提出了一种基于Omni-Scale Block的1D-CNN模型，可以通过包含多个质数的一组核大小有效地覆盖不同数据集中的最佳Receptive Field大小，并达到了四个时间序列基准测试的最先进性能。

Omni-Scale CNNs: 一种简单而有效的时间序列分类卷积核大小配置方法