papers AI Learner
The Github is limit! Click to go to the new site.

Reducing the dilution: An analysis of the information sensitiveness of capsule network with a practical improvement method

2019-05-02
Zonglin Yang, Xinggang Wang

Abstract

Capsule network has shown various advantages over convolutional neural network (CNN). It keeps more precise spatial information than CNN and uses equivariance instead of invariance during inference and highly potential to be a new effective tool for visual tasks. However, the current capsule networks have incompatible performance with CNN when facing datasets with background and complex target objects and are lacking in universal and efficient regularization method. We analyze a main reason of the incompatible performance as the conflict between information sensitiveness of capsule network and unreasonably higher activation value distribution of capsules in primary capsule layer. Correspondingly, we propose a practical improvement method by restraining the activation value of capsules in primary capsule layer to suppress non-informative capsules and highlight discriminative capsules. In the experiments, the method has achieved better performances on various mainstream datasets. In addition, the proposed improvement methods can be seen as a suitable, simple and efficient regularization method that can be generally used in capsule network.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.10588

PDF

http://arxiv.org/pdf/1903.10588


Similar Posts

Comments