Abstract—Image classification is one of the predominant tasks in computer vision. So far, there are many approaches in image classification, and the most typical methods are Convolutional Neural Networks (CNN), BOF-based algorithms, etc. Most of these methods have a good performance, but there are still some limitations. Capsule Network (CapsNet) is the most advanced algorithm, which realizes the operation based on active vector and dynamic routing, and can overcome limitations of the original algorithm. This paper attempts to apply CapsNet into image classification as well as another two efficient classification methods, which are CNN and Fully Convolutional Network (FCN). We use two datasets: MNIST and CIFAR-10 to train our model and tested the networks. Finally, compare and evaluate their performances in aspects of time cost, loss, accuracy and the number of parameters.
Index Terms—Capsule network, convolutional neural networks, full convolutional neural network, image classification.
Xuefeng Jiang, Yikun Wang, Wenbo Liu, and Junrui Liu are with the School of Computing, Northwestern Polytechnical University, Xi'an 710072, Shaanxi, P.R. China (e-mail: jxf@nwpu.edu.cn, yikunwang6@163.com, osmium@mail.nwpu.edu.cn, liu.junrui@nwpu.edu.cn).
Shuying Li is with the School of Automation, Xi'an University of Posts & Telecommunications, Xi'an 710121, Shaanxi, P.R. China (e-mail: angle_lisy@163.com).
Cite: Xuefeng Jiang, Yikun Wang, Wenbo Liu, Shuying Li, and Junrui Liu, "CapsNet, CNN, FCN: Comparative Performance Evaluation for Image Classification," International Journal of Machine Learning and Computing vol. 9, no. 6, pp. 840-848, 2019.
Copyright © 2019 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).