Path Capsule Networks

Amer, Mohammed; Maul, Tomás

doi:10.1007/s11063-020-10273-0

Cited by 22 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNN has a poor learning effect on spatial location, so when identifying such traffic signs, it will lose detailed information such as position and posture. CapsNets [15] [16] [17] handles traffic sign images more than CNN in spatial position. The entire learning process of capsnets is transmitted from the bottom layer to the upper layer in the form of "capsules", which encapsulates multi-dimensional features, thus reducing the number of training samples while retaining the characteristics of traffic signs with less probability of occurrence.…”

Section: Traffic Sign Recognition Methods Based On Deep Learningmentioning

confidence: 99%

Multi-Scale CapsNet: A Novel Traffic Sign Recognition Method

Chen¹,

Deng²

2019

FSP

View full text Add to dashboard Cite

Convolutional Neural Networks (CNNs) have performed very well on image classification tasks, but CNNs is insensitive to detailed image information and requires a large amount of training data and time. Capsule Networks(CapsNets) can solve this problem very well, but the Baseline CapsNet model is very shallow, and the extraction of low-level features is not enough. We propose a Multi-Scale Capsule Network (Multi-Scale CapsNet), by extracting the low-level features of images with multi-channel convolution of multiple convolution kernels, so extracted features are more diverse, then passing from the bottom layer to the upper layer in the form of a "capsule", which encapsulats the multidimensional features of the image in the form of a vector, thus the features are saved in the network, rather than being recovered after being lost. In the German Traffic Sign Recognition Benchmark(GTSRB), we obtained competitive results with the accuracy of 99.4%, which is better than the human performance of 98.81% and the Multi-Scale Convolutional Neural Network(MS-CNN) of 97.33%.

show abstract

Section: Traffic Sign Recognition Methods Based On Deep Learningmentioning

confidence: 99%

Multi-Scale CapsNet: A Novel Traffic Sign Recognition Method

Chen¹,

Deng²

2019

FSP

View full text Add to dashboard Cite

show abstract

“…To address the drawbacks of the standard CapsNet architecture such as the high number of trainable parameters and the limited representational power of capsules, Path CapsNet was proposed by Amer and Maul [19]. They studied the model to include more expressiveness and abstraction due to the deep path modelling paradigm of MLCN to exhibit multipath parallel processing for a diversifying effect on the learned representations.…”

Section: IImentioning

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

“…Such data augments are reasonable because some features of the image are enhanced after pre-processing. For example, we often adopt canny algorithm to enhance the edge feature, which can be seen in the 2th and 10th columns of Based on previous work [35], we find that the number of lanes is one of the most important factors to the result of classification in the parallel network. Therefore, we assume that different input and mixing ratios will have a great impact on the experimental results.…”

Section: F Feature Selectionmentioning

confidence: 99%

Multi-Lane Capsule Network for Classifying Images With Complex Background

Chang¹,

Liu²

2020

IEEE Access

View full text Add to dashboard Cite

Capsule Network (CapsNet) is a novel structure for deep neural network, mapping the region of target instance to vectors and matrices rather than scalars. This process is enabled by dynamic routing algorithm which help CapsNet to achieve more robust capacity with fewer parameters than traditional CNNs. However, one drawback of Capsule is that it turns to account for everything in the image, which leads to a poor performance when the backgrounds are too varied to model with a reasonable sized net. We proposed a multi-lane capsule network with strict-squash (MLSCN) to solve this problem. In MLSCN, we designed a novel Capsule based network structure, replaced the Squash function and optimized the implementation of dropout. To validate modification proposed in the paper, we conducted extensive experiments on three public datasets which include MNIST, affNIST and CIFAR10. Ablation experiments were also conducted to analyze contributions of each component of MLSCN. Experimental results show that MLSCN outperforms the original CapsNet in multiple benchmarks. Our model boosts the classification accuracy of CIFAR10 about 17% with negligible parameter increase compare to original CapsNet. Besides, the proposed model achieves an accuracy of 65.37%, while original CapsNet is only 41.62% on MNIST-BC. INDEX TERMS Capsule network, multi-lane, strict-squash, drop-circuit, lane-filter, complex background.

show abstract

Path Capsule Networks

Cited by 22 publications

References 26 publications

Multi-Scale CapsNet: A Novel Traffic Sign Recognition Method

Multi-Scale CapsNet: A Novel Traffic Sign Recognition Method

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

Multi-Lane Capsule Network for Classifying Images With Complex Background

Contact Info

Product

Resources

About