跳到主要导航 跳到搜索 跳到主要内容

Enhancing classification efficiency in capsule networks through windowed routing: tackling gradient vanishing, dynamic routing, and computational complexity challenges

  • Northwestern Polytechnical University Xian
  • China State Ship building Co. Ltd

科研成果: 期刊稿件 › 文章 › 同行评审

2 引用 (Scopus)

摘要

Capsule networks overcome the two drawbacks of convolutional neural networks: weak rotated object recognition and poor spatial discrimination. However, they still have encountered problems with complex images, including high computational cost and limited accuracy. To address these challenges, this work has developed effective solutions. Specifically, a novel windowed dynamic up-and-down attention routing process is first introduced, which can effectively reduce the computational complexity from quadratic to linear order. A novel deconvolution-based decoder is also used to further reduce the computational complexity. Then, a novel LayerNorm strategy is used to pre-process neuron values in the squash function. This prevents saturation and mitigates the gradient vanishing problem. In addition, a novel gradient-friendly network structure is developed to facilitate the extraction of complex features with deeper networks. Experiments show that our methods are effective and competitive, outperforming existing techniques.

源语言英语
期刊论文编号45
期刊Complex and Intelligent Systems
卷11
期1
DOI
出版状态已出版 - 1月 2025

学术指纹

探究 'Enhancing classification efficiency in capsule networks through windowed routing: tackling gradient vanishing, dynamic routing, and computational complexity challenges' 的科研主题。它们共同构成独一无二的学术指纹。

引用此