{Jarosław Kurek Izabella Antoniuk Michał Bukowski}

Abstract

In this paper, we present an improved efficient capsule network (CN) model for the classification of the Kuzushiji-MNIST andKuzushiji-49 benchmark datasets. CNs are a promising approach in the field of deep learning, offering advantages such as robustness, bettergeneralization, and a simpler network structure compared to traditional convolutional neural networks (CNNs). Proposed model, based on theEfficient CapsNet architecture, incorporates the self-attention routing mechanism, resulting in improved efficiency and reduced parameter count.The experiments conducted on the Kuzushiji-MNIST and Kuzushiji-49 datasets demonstrate that the model achieves competitive performance,ranking within the top ten solutions for both benchmarks. Despite using significantly fewer parameters compared to higher-rated competitors,presented model achieves comparable accuracy, with overall differences of only 0.91% and 1.97% for the Kuzushiji-MNIST and Kuzushiji-49 datasets, respectively. Furthermore, the training time required to achieve these results is substantially reduced, enabling training on non-specialized workstations. The proposed novelties of capsule architecture, including the integration of the self-attention mechanism and theefficient network structure, contribute to the improved efficiency and performance of presented model. These findings highlight the potential ofCNs as a more efficient and effective approach for character classification tasks, with broader applications in various domains.