Two-phase Dynamic Routing for Micro and Macro-level Equivariance in Multi-Column Capsule Networks

Mandal, Bodhisatwa; Sarkhel, Ritesh; Ghosh, Swarnendu; Das, Nibaran; Nasipuri, Mita

doi:10.1016/j.patcog.2020.107595

Cited by 15 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the iteration methods to train a coupling coefficient, J. Rajasegaran et al [34] propose a new dynamic routing based on 3D convolution, which predicts each capsule 3D convolution operation. B. Mandal et al [35] divide dynamic routing into two steps to calculate the consistency between different levels of capsules. Also, they [36], [37] introduce the attention mechanism into the routing to deal with the primary capsules which have more information.…”

Section: A Capsule Networkmentioning

confidence: 99%

An Improved Capsule Network Based on Capsule Filter Routing

et al. 2021

View full text Add to dashboard Cite

Capsule network (CapsNet) is a novel type of network that can retain spatial information, because each capsule can integrate more information than scalar-output features. However, the CapsNet learns all the features in the input image due to the lack of pooling operation, and there is no connection between different layers in the multi-layer network structure. In this paper, we propose an improved capsule network (CapsNet) based on Capsule Filter Routing (CFR) to address this problem, namely CFR-CapsNet. Firstly, we propose a new routing method called CFR for filtering capsules based on capsule activation values, which can speed up the operation of the model, and then introduce a self-attention mechanism to improve the performance of the primary capsule in the capsule space. Furthermore, in the multi-layer network structure, we transmit the information of the classified capsule with the largest activation value in the previous capsule layer to the primary capsules of the next layer, which improves the relevance of the overall structure. We conduct experiments on Fashion-MNIST, SVHN, and CIFAR-10/100, and the experimental results show that our method can improve the performance of the CapsNet more effectively than other state-of-the-arts.

show abstract

Section: A Capsule Networkmentioning

confidence: 99%

An Improved Capsule Network Based on Capsule Filter Routing

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In another work (Ding et al, 2019), capsules are partitioned into several groups and corresponding high-level capsules are obtained by group reconstruction routing and then maximum pooling is used to avoid overfitting. In (Mandal et al, 2021) a hierarchical learning and two-phase dynamic routing approach has been used in multi-column CapsNet to provide macro and micro-level equivariance. In (Long et al, 2021) feature extraction has been provided by three convolutional layers instead of one in the modified CapsNet model.…”

Section: Capsnet Based Image Classification Techniquesmentioning

confidence: 99%

Analysis of Capsule Networks for Image Classification

2021

Proceedings of the 15th International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing (CGV

View full text Add to dashboard Cite

Recently, the interest in convolutional neural networks have grown exponentially for image classification. Their success is based on the ability to learn hierarchical and meaningful image representation that results in a feature extraction technique which is general, flexible and can encode complex patterns. However, these networks have some drawbacks. For example, they need a large number of labeled data, lose valuable information (about the internal properties, such as shape, location, pose and orientation in an image and their relationships) in the pooling and are not able to encode deformation information. Therefore, capsule based networks have been introduced as an alternative to convolutional neural networks. Capsules are a group of neurons (logistic units) representing the presence of an entity and the vector indicating the relationship between features by encoding instantiation parameters. Unlike convolutional neural networks, maximum pooling layers are not employed in a capsule network, but a dynamic routing mechanism is applied iteratively in order to decide the coupling of capsules between successive layers. In other words, training between capsule layers is provided with a routing-by-agreement method. However, capsule networks and their properties to provide high accuracy for image classification have not been sufficiently investigated. Therefore, this paper aims (i) to point out drawbacks of convolutional networks, (ii) to examine capsule networks, (iii) to present advantages, weaknesses and strengths of capsule networks proposed for image classification.

show abstract

“…Multi-lane capsule networks [13] are resource efficient networks that can perform parallel processing at a reduced cost and deliver high performing models. The multiple dataindependent lanes in the model would be capable of learning distinct features from the training dataset through different dimensions of the vectors and add resilience to the network structure [14].…”

Section: Introductionmentioning

confidence: 99%

Multi-Lane Capsule Network Architecture for Detection of COVID-19

Sridhar

Sanagavarapu

2021

2021 2nd International Conference on Intelligent Engineering and Management (ICIEM)

View full text Add to dashboard Cite

The COVID-19 pandemic in the world has given rise to a lot of research done in the field of medical imaging using deep learning and artificial intelligence methods for the detection and prognosis of the disease. Capsule Networks (CapsNet) perform image classification by identifying the spatial location and orientation of features within the images. In this paper, a Multi-lane Capsule Neural Networks (MLCN) model is introduced that performs dynamic routing networks with dimensionally distinct parallel lanes, replacing the traditional pooling operations in Convolutional Neural Networks (CNN). With the use of parallel capsules, feature orientation identification at any given part of the image is improved. The MLCN model has been studied in this paper using the X-ray images collected from patients tested for COVID-19 and its performance is evaluated using a number of metrics. It has been observed that the performance of the constructed CapsNet model achieved a testing accuracy of 96.8% with the F-1 score 97.19% performing better than the existing state-of-the-art models.

show abstract

Two-phase Dynamic Routing for Micro and Macro-level Equivariance in Multi-Column Capsule Networks

Cited by 15 publications

References 18 publications

An Improved Capsule Network Based on Capsule Filter Routing

An Improved Capsule Network Based on Capsule Filter Routing

Analysis of Capsule Networks for Image Classification

Multi-Lane Capsule Network Architecture for Detection of COVID-19

Contact Info

Product

Resources

About