Group Feedback Capsule Network

Xinpeng Ding, Nannan Wang, Xinbo Gao, Jie Li, Xiaoyu Wang, Tongliang Liu

Abstract

In capsule networks (CapsNets), the capsule is made up of collections of neurons. Their adjacent capsule layers are connected using routing-by-agreement mechanisms in an unsupervised way. The routing-by-agreement mechanisms have two main drawbacks: a) too many parameters and high computation complexity; b) the cluster distribution assumptions of these routing mechanisms may not hold in some complex real-world data. In this paper, we propose a novel Group Feedback Capsule Network (GF-CapsNet) which adopts a supervised routing strategy called group-routing. Compared with the previous routing strategies which globally transform each capsule, Group-routing equally splits capsules into groups where capsules locally share the same transformation weights, reducing routing parameters. To address the second drawback, we devise a distance network to directly predict capsules in a supervised way without making distribution assumptions. Our proposed group-routing captures local information of low-level capsules by group-wise transformation and supervisedly predicts high-level ones in a feedback way to address two drawbacks respectively. We conduct experiments on CIFAR-10/100 and SVHN datasets and the results show that our method can perform better against state-of-the-arts.
BibTeX
@article{ding2020group,
  author = {Xinpeng Ding and Nannan Wang and Xinbo Gao and Jie Li and Xiaoyu Wang and Tongliang Liu},
  title = {{Group Feedback Capsule Network}},
  journal = {IEEE Trans. Image Process.},
  year = {2020},
  url = {https://openreview.net/forum?id=LVYk33bWgQd},
}

Loading related content...

Figure