Sparse CapsNet with explicit regularizer

作者：

Highlights：

• A novel sparse capsule network (CapsNet) with explicit regularizer is proposed.

• Both component-wise and filter-wise sparsity are considered for weight compression.

• A new stochastic proximal algorithm is designed to train the sparse CapsNet.

• Numerical experiments validate the effectiveness and efficiency of our method.

摘要

•A novel sparse capsule network (CapsNet) with explicit regularizer is proposed.•Both component-wise and filter-wise sparsity are considered for weight compression.•A new stochastic proximal algorithm is designed to train the sparse CapsNet.•Numerical experiments validate the effectiveness and efficiency of our method.

论文关键词：Capsule network,Model compression,Sparse regularization,Proximal gradient descent

论文评审过程：Received 27 October 2020, Revised 2 December 2021, Accepted 3 December 2021, Available online 6 December 2021, Version of Record 20 December 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108486