Res-CapsNet: Residual Capsule Network for Data Classification

Jia, Xibin; Li, Jianqiao; Zhao, Baiting; Guo, Yongcun; Huang, Yourui

doi:10.1007/s11063-022-10806-9

Cited by 9 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CapsNet performance is relatively poor in Fashion-MNIST [8] and CIFAR10 [9]. There were two reasons were reported to cause this disparity [10,11,12,6,13]: 1) CapsNet has only two feature extraction layers, leading to the inability to extract semantic information for dynamic routing algorithm; 2) The reconstruction module is ineffective for complicated datasets with noisy backgrounds.…”

Section: Introductionmentioning

confidence: 99%

AlexCapsNet: an integrated architecture for image classification with noise and many categories

Bao,

Jin,

2024

Preprint

View full text Add to dashboard Cite

Capsule network (CapsNet) is a pioneering architecture that can encode the image properties into vectors rather than scalars, addressing the limitations of traditional Convolutional Neural Networks (CNNs). This process is achieved by dynamic routing algorithms to maintain the spatial hierarchies. However CapsNet may decreases its efficacy in complex datasets, such as CIFAR-10. To address this problem, we propose AlexCapsNet architecture, in which the classic classification model AlexNet is used as the feature extraction layer. Such a layer allows CapsNet to capture deeper and more semantic features. Comprehensive evaluation with five datasets shows that AlexCapsNet has achieved improved performance compared to the baseline and other variants of CapsNet. In addition, we also introduce the Shallow-AlexNet module, revealing that deeper feature extraction layers are suitable for datasets with fewer categories and shallower feature extraction layers are more effective for datasets with many categories, owing to inherent category differences. Moreover, our investigation into the reconstruction module shows that noise in the datasets helps degrade the performance of the reconstruction module.

show abstract

Section: Introductionmentioning

confidence: 99%

AlexCapsNet: an integrated architecture for image classification with noise and many categories

Bao,

Jin,

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Nonetheless, some studies in the literature have used residual blocks in order to avoid the problem of overfitting and vanishing gradient that may occur as the number of layers increases. [7][8][9][10][11][12][13] Examination of the literature indicates that using residual blocks enhances CapsNet's feature extraction capability. Furthermore, residual blocks in the existing models are often used back-to-back.…”

Section: Introductionmentioning

confidence: 99%

“…While more basic features such as edges and corners are extracted with the first layer, more attributed feature maps are obtained as the number of layers increases. Nonetheless, some studies in the literature have used residual blocks in order to avoid the problem of overfitting and vanishing gradient that may occur as the number of layers increases 7–13 . Examination of the literature indicates that using residual blocks enhances CapsNet's feature extraction capability.…”

Section: Introductionmentioning

confidence: 99%

MResCaps: Enhancing capsule networks with parallel lanes and residual blocks for high‐performance medical image classification

Şengül,

Özkan

2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The classification of medical images enables physicians to perform expeditious and accurate data analysis, increasing the chances of timely disease diagnosis and early intervention to the patient. However, classification is a time‐consuming and labour intensive process when done manually. The Capsule Network (CapsNet) architecture has advantages in accurately and quickly classifying medical images due to its ability to evaluate images within part‐whole relationships, robustness to data rotations and affine transformations, and good performance on small datasets. However, CapsNet may demonstrate low performance on complex datasets. In this study, a new CapsNet model named MResCaps is proposed to overcome this disadvantage and enhance its performance on complex images. MResCaps utilizes an increasing number of residual blocks in each layer in parallel lane to obtain rich feature maps at different levels, aiming to achieve high success in the classification of various medical images. To evaluate the model's performance, the CIFAR10 dataset and the DermaMNIST, PneumoniaMNIST, and OrganMNIST‐S datasets from the MedMNIST dataset collection are used. MResCaps outperformed CapsNet by 20% in terms of accuracy on the CIFAR10 dataset. In addition, AUC values of 96.25%, 96.30%, and 97.12% were achieved in DermaMNIST, PneumoniaMNIST, and OrganMNIST‐S datasets, respectively. The results show that the proposed new model MResCaps improves the performance of CapsNet in the classification of complex and medical images. Furthermore, the model has demonstrated a better performance in comparison with extant studies in the literature. This study aims to contribute significantly to the literature by introducing a novel perspective on CapsNet‐based architectures for the classification of medical images through a parallel‐laned architecture and a rich feature capsule‐focused approach.

show abstract

XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers for Convolutional Neural Networks

Sun,

Fard,

Mahoor

2023

J Intell Robot Syst

View full text Add to dashboard Cite

Res-CapsNet: Residual Capsule Network for Data Classification

Cited by 9 publications

References 20 publications

AlexCapsNet: an integrated architecture for image classification with noise and many categories

AlexCapsNet: an integrated architecture for image classification with noise and many categories

MResCaps: Enhancing capsule networks with parallel lanes and residual blocks for high‐performance medical image classification

XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers for Convolutional Neural Networks

Contact Info

Product

Resources

About