Two-phase Dynamic Routing for Micro and Macro-level Equivariance in Multi-Column Capsule Networks

作者：

Highlights：

• We propose two-phase dynamic routing for micro and macro level aggregation of multiple region-specific capsule networks.

• We demonstrate the superiority of our model over standard capsule networks and state-of-the-art multicolumn architectures.

• We evaluate our models on 7 publicaly available datasets.

摘要

•We propose two-phase dynamic routing for micro and macro level aggregation of multiple region-specific capsule networks.•We demonstrate the superiority of our model over standard capsule networks and state-of-the-art multicolumn architectures.•We evaluate our models on 7 publicaly available datasets.

论文关键词：Dynamic routing,Routing by agreement,Multi-level,Multi-column neural network,Capsule networks

论文评审过程：Received 13 August 2019, Revised 2 July 2020, Accepted 15 August 2020, Available online 18 August 2020, Version of Record 23 August 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107595