Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network

被引:6
|
作者
Shiri, Pouya [1 ]
Baniasadi, Amirali [1 ]
机构
[1] Univ Victoria, Elect & Comp Engn Fac, Victoria, BC, Canada
来源
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY | 2022年 / 94卷 / 07期
基金
加拿大自然科学与工程研究理事会;
关键词
Capsule Networks; CapsNet; Deep Learning; Fast CapsNet;
D O I
10.1007/s11265-021-01731-6
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A Capsule Network (CapsNet) is a relatively new classifier and one of the possible successors of Convolutional Neural Networks (CNNs). CapsNet maintains the spatial hierarchies between the features and outperforms CNNs at classifying images including overlapping categories. Even though CapsNet works well on small-scale datasets such as MNIST, it fails to achieve a similar level of performance on more complicated datasets and real applications. In addition, CapsNet is slow compared to CNNs when performing the same task and relies on a higher number of parameters. In this work, we introduce Convolutional Fully-Connected Capsule Network (CFC-CapsNet) to address the shortcomings of CapsNet by creating capsules using a different method. We introduce a new layer (CFC layer) as an alternative solution to creating capsules. CFC-CapsNet produces fewer, yet more powerful capsules resulting in higher network accuracy. Our experiments show that CFC-CapsNet achieves competitive accuracy, faster training and inference and uses less number of parameters on the CIFAR-10, SVHN and Fashion-MNIST datasets compared to conventional CapsNet.
引用
收藏
页码:645 / 658
页数:14
相关论文
共 50 条
  • [31] Memristive Residual CapsNet: A hardware friendly multi-level capsule network
    He, Peng
    Zhou, Yue
    Duan, Shukai
    Hu, Xiaofang
    NEUROCOMPUTING, 2022, 496 : 1 - 10
  • [32] Fast Convergent Capsule Network with Applications in MNIST
    Zou, Xianli
    Duan, Shukai
    Wang, Lidan
    Zhang, Jin
    ADVANCES IN NEURAL NETWORKS - ISNN 2018, 2018, 10878 : 3 - 10
  • [33] Image Synthesis with a Convolutional Capsule Generative Adversarial Network
    Bass, Cher
    Dai, Tianhong
    Billot, Benjamin
    Arulkumaran, Kai
    Creswell, Antonia
    Clopath, Claudia
    De Paola, Vincenzo
    Bharath, Anil Anthony
    INTERNATIONAL CONFERENCE ON MEDICAL IMAGING WITH DEEP LEARNING, VOL 102, 2019, 102 : 39 - 62
  • [34] Disease Detection of Lily Based on Convolutional Capsule Network
    Ding Y.
    Zhang J.
    Li M.
    Li, Minzan (limz@cau.edu.cn), 1600, Chinese Society of Agricultural Machinery (51): : 246 - 251and331
  • [35] FULLY-CONNECTED TENSOR NETWORK DECOMPOSITION FOR ROBUST TENSOR COMPLETION PROBLEM
    Liu, Yun-Yang
    Zhao, Xi-Le
    Song, Guang-Jing
    Zheng, Yu-Bang
    Ng, Michael K.
    Huang, Ting-Zhu
    INVERSE PROBLEMS AND IMAGING, 2023, : 208 - 238
  • [36] SVD-based algorithms for fully-connected tensor network decomposition
    Wang, Mengyu
    Li, Hanyu
    COMPUTATIONAL & APPLIED MATHEMATICS, 2024, 43 (05):
  • [37] Throughput analysis for fully-connected ad hoe network with multiuser detection
    Qian, XC
    Zheng, BY
    Yu, GJ
    PARALLEL AND DISTRIBUTED PROCESSING AND APPLICATIONS, 2005, 3758 : 1101 - 1112
  • [38] Lightweight Fully-Connected Tensorial Mapping Network for Hyperspectral Image Classification
    Lin, Zhi-Xin
    Zheng, Yu-Bang
    Ma, Tian-Yu
    Wang, Rui
    Li, Heng-Chao
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2024, 52 (10): : 3541 - 3551
  • [39] Optimal Timeslot Assignment in a Fully-connected Unmanned Aerial Vehicles Network
    Zhang, Jing
    Huang, Zixuan
    Sun, Bingyu
    2024 IEEE/CIC INTERNATIONAL CONFERENCE ON COMMUNICATIONS IN CHINA, ICCC, 2024,
  • [40] Modified Capsule Neural Network (Mod-CapsNet) for Indoor Home Scene Recognition
    Basu, Amlan
    Kaewrak, Keerati
    Petropoulakis, Lykourgos
    Di Caterina, Gaetano
    Soraghan, John J.
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,