Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification. (arXiv:2002.10061v3 [cs.LG] UPDATED)

The Receptive Field (RF) size has been one of the most important factors for
One Dimensional Convolutional Neural Networks (1D-CNNs) on time series
classification tasks. Large efforts have been taken to choose the appropriate
size because it has a huge influence on the performance and differs
significantly for each dataset. In this paper, we propose an Omni-Scale block
(OS-block) for 1D-CNNs, where the kernel sizes are decided by a simple and
universal rule. Particularly, it is a set of kernel …

arxiv classification cnns kernel lg scale series time time series