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
  • [41] Robustness comparison between the capsule network and the convolutional network for facial expression recognition
    Donghui Li
    Xingcong Zhao
    Guangjie Yuan
    Ying Liu
    Guangyuan Liu
    Applied Intelligence, 2021, 51 : 2269 - 2278
  • [42] Robustness comparison between the capsule network and the convolutional network for facial expression recognition
    Li, Donghui
    Zhao, Xingcong
    Yuan, Guangjie
    Liu, Ying
    Liu, Guangyuan
    APPLIED INTELLIGENCE, 2021, 51 (04) : 2269 - 2278
  • [43] PTC-CapsNet: capsule network for papillary thyroid carcinoma pathological images classification
    Han B.
    Han Y.
    Li H.
    Gao X.
    Multimedia Tools and Applications, 2025, 84 (4) : 1907 - 1925
  • [44] Expression Recognition Method Based on Convolutional Neural Network and Capsule Neural Network
    Wang, Zhanfeng
    Yao, Lisha
    CMC-COMPUTERS MATERIALS & CONTINUA, 2024, 79 (01): : 1659 - 1677
  • [45] FL-CapsNet: facial localization augmented capsule network for human emotion recognition
    Bellamkonda Sivaiah
    N. P. Gopalan
    C. Mala
    Settipalli Lavanya
    Signal, Image and Video Processing, 2023, 17 : 1705 - 1713
  • [46] A random sampling algorithm for fully-connected tensor network decomposition with applications
    Wang, Mengyu
    Cui, Honghua
    Li, Hanyu
    COMPUTATIONAL & APPLIED MATHEMATICS, 2024, 43 (04):
  • [47] FL-CapsNet: facial localization augmented capsule network for human emotion recognition
    Sivaiah, Bellamkonda
    Gopalan, N. P.
    Mala, C.
    Lavanya, Settipalli
    SIGNAL IMAGE AND VIDEO PROCESSING, 2023, 17 (04) : 1705 - 1713
  • [48] EMG-CapsNet: Elu Multiplication Gate Capsule Network for Complex Images Classification
    El Alaoui-Elfels, Omaima
    Gadi, Taoufiq
    PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING AND PATTERN RECOGNITION (SOCPAR 2021), 2022, 417 : 97 - 108
  • [49] Bi-CapsNet: A Binary Capsule Network for EEG-Based Emotion Recognition
    Liu, Yu
    Wei, Yi
    Li, Chang
    Cheng, Juan
    Song, Rencheng
    Chen, Xun
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2023, 27 (03) : 1319 - 1330
  • [50] BDARS_CapsNet: Bi-Directional Attention Routing Sausage Capsule Network
    Ning, Xin
    Tian, Weijuan
    Li, Weijun
    Lu, Yueyue
    Nie, Shuai
    Sun, Linjun
    Chen, Ziheng
    IEEE ACCESS, 2020, 8 : 59059 - 59068