ME-CapsNet: A Multi-Enhanced Capsule Networks with Routing Mechanism

TL;DR

ME-CapsNet enhances capsule networks by integrating deeper convolutional layers with Squeeze-Excitation modules, improving feature extraction and spatial-channel calibration, leading to superior performance on complex datasets.

Contribution

Introduces ME-CapsNet, combining deeper convolutions and capsule layers with dynamic channel recalibration to improve complex dataset performance.

Findings

Outperforms existing models on complex datasets

Achieves higher accuracy with minimal complexity

Effectively enhances feature extraction and calibration

Abstract

Convolutional Neural Networks need the construction of informative features, which are determined by channel-wise and spatial-wise information at the network's layers. In this research, we focus on bringing in a novel solution that uses sophisticated optimization for enhancing both the spatial and channel components inside each layer's receptive field. Capsule Networks were used to understand the spatial association between features in the feature map. Standalone capsule networks have shown good results on comparatively simple datasets than on complex datasets as a result of the inordinate amount of feature information. Thus, to tackle this issue, we have proposed ME-CapsNet by introducing deeper convolutional layers to extract important features before passing through modules of capsule layers strategically to improve the performance of the network significantly. The deeper convolutional layer includes blocks of Squeeze-Excitation networks which use a stochastic sampling approach for progressively reducing the spatial size thereby dynamically recalibrating the channels by reconstructing their interdependencies without much loss of important feature information. Extensive experimentation was done using commonly used datasets demonstrating the efficiency of the proposed ME-CapsNet, which clearly outperforms various research works by achieving higher accuracy with minimal model complexity in complex datasets.