A Robustness Enhanced Capsule Network with Regularization
2023 6th International Conference on Intelligent Autonomous Systems (ICoIAS)(2023)
Abstract
This paper aims to guarantee the robustness of capsule networks (CapsNets) by regularization in the construction of primary capsules and higher-level capsules. A novel CapsN et, namely robustness enhanced CapsNet with regularization (RE-CapsN et) has been put forward by exploiting the equivariant spatial relationship and the invariant descriptors of parts. The main idea of RE-CapsNet is three-fold: 1) the regularization for poses and descriptors of capsules combined with attention modules is introduced to establish the primary capsules; 2) the utilization of regularization contributes greatly to the robustness, and the adoption of attention modules and regularization gives rise to good interpretability of RE-CapsNet; 3) the comparison experiments on several datasets reveal the RE-CapsNet generalizes better on unfamiliar viewpoints with affine transformations.
MoreTranslated text
Key words
capsule network,image classification,robustness,equivariance
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined