Results 11 to 20 of about 157,621 (267)
Deep Tensor Capsule Network [PDF]
IEEE Access, 2020 Capsule network is a promising model in computer vision. It has achieved excellent results on simple datasets such as MNIST, but the performance deteriorates as data becomes complicated.
Kun Sun +3 more
doaj +2 more sources
The Multi-Lane Capsule Network (MLCN) [PDF]
IEEE Signal Processing Letters, 2019 We introduce Multi-Lane Capsule Networks (MLCN), which are a separable and resource efficient organization of Capsule Networks (CapsNet) that allows parallel processing, while achieving high accuracy at reduced cost.
Borin, Edson +2 more
core +2 more sources
Residual Vector Capsule: Improving Capsule by Pose Attention
IEEE Access, 2021 The convolutional neural network has significantly improved the accuracy of image recognition; however, it performs in a fragile manner when we apply viewpoint transformation or add noise to the image.
Ning Xie, Xiaoxia Wan
doaj +2 more sources
Quaternion Capsule Networks [PDF]
2020 25th International Conference on Pattern Recognition (ICPR), 2021 Capsules are grouping of neurons that allow to represent sophisticated information of a visual entity such as pose and features. In the view of this property, Capsule Networks outperform CNNs in challenging tasks like object recognition in unseen viewpoints, and this is achieved by learning the transformations between the object and its parts with the ...
Baris Özcan +2 more
openaire +3 more sources
Limitation of capsule networks [PDF]
Pattern Recognition Letters, 2021 A recently proposed method in deep learning groups multiple neurons to capsules such that each capsule represents an object or part of an object. Routing algorithms route the output of capsules from lower-level layers to upper-level layers. In this paper, we prove that state-of-the-art routing procedures decrease the expressivity of capsule networks ...
David Peer +2 more
openaire +2 more sources
UCaps Network Based on EM-Routing Algorithm for Medical Image Segmentation [PDF]
Jisuanji gongcheng, 2022 The existing medical image segmentation networks are limited in segmentation accuracy, and often lose image information as well as produce vague segmentation boundary.In this paper, we propose a multi-label image segmentation network named UCaps, which ...
WANG Wenxin, HE Yuhang, CHEN Gang
doaj +1 more source
Improved Two-Branch Capsule Network for Hyperspectral Image Classification [PDF]
Jisuanji kexue yu tansuo, 2022 The method based on the dual-channel capsule network extracts spectral information and spatial informa-tion separately in two channels, which not only retains the feature extraction method of the dual-channel convolu-tional neural network, but also ...
ZHANG Haitao, CHAI Simin
doaj +1 more source
Quantum Science and Technology, 2022 Abstract Capsule networks (CapsNets), which incorporate the paradigms of connectionism and symbolism, have brought fresh insights into artificial intelligence (AI). The capsule, as the building block of CapsNets, is a group of neurons represented by a vector to encode different features of an entity.
Zidu Liu +4 more
openaire +2 more sources
Journal of King Saud University - Computer and Information Sciences, 2022 Modern day computer vision tasks requires efficient solution to problems such as image recognition, natural language processing, object detection, object segmentation and language translation. Symbolic Artificial Intelligence with its hard coding rules is incapable of solving these complex problems resulting in the introduction of Deep Learning (DL ...
Patrick Kwabena Mensah +3 more
openaire +2 more sources
CoRR, 2022 Capsule networks are a class of neural networks that achieved promising results on many computer vision tasks. However, baseline capsule networks have failed to reach state-of-the-art results on more complex datasets due to the high computation and memory requirements.
Josef Gugglberger +2 more
openaire +3 more sources