Results 241 to 250 of about 83,262 (269)
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, Antonio Rodriguez-Sanchez
exaly +3 more sources
Breaking CAPTCHA with Capsule Networks
Neural Networks, 2022 Convolutional Neural Networks have achieved state-of-the-art performance in image classification. Their lack of ability to recognise the spatial relationship between features, however, leads to misclassification of the variants of the same image. Capsule Networks were introduced to address this issue by incorporating the spatial information of image ...
Ionela Georgiana Mocanu, Vaishak Belle
exaly +4 more sources
Capsule Networks with Routing Annealing
Lecture Notes in Computer Science, 2021 Capsule Networks overcome some shortcomings of convolutional neural networks organizing neurons into groups of capsules. Capsule layers are dynamically connected by means of an iterative routing mechanism, which models the connection strengths between capsules from different layers.
Riccardo Renzulli +2 more
exaly +4 more sources
Some of the next articles are maybe not open access.
Related searches:
Related searches:
International Journal of Machine Learning and Cybernetics, 2021
The capsule network (CapsNet) is a novel network model that can learn spatial information in images. However, the performance of CapsNet on complex datasets (such as CIFAR10) is limited and it requires a large number of parameters. These disadvantages make CapsNet less useful, especially in some resource-constrained devices.
Kun Sun +3 more
openaire +1 more source
The capsule network (CapsNet) is a novel network model that can learn spatial information in images. However, the performance of CapsNet on complex datasets (such as CIFAR10) is limited and it requires a large number of parameters. These disadvantages make CapsNet less useful, especially in some resource-constrained devices.
Kun Sun +3 more
openaire +1 more source
CNN to Capsule Network Transformation
2020 Digital Image Computing: Techniques and Applications (DICTA), 2020Capsule Network has been recently proposed which outperforms CNN in specific tasks. Due to the network architecture differences between Capsule Network and CNN, Capsule Network could not use transfer learning which is very frequently used in CNN. In this paper, we propose a transfer learning method which can easily transfer CNN to Capsule Network.
Takumi Sato, Kazuhiro Hotta
openaire +1 more source
MapReduce-based Capsule Networks
2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS), 2019Currently, artificial intelligence technology is attracting much attention, and image processing field is also making remarkable progress in recognition rate through CNN models. Furthermore, Capsule Network which is flexible in changing pose of image is being studied in various fields by improving disadvantage of Pooling Layer of CNN model.
Sun-Jin Park, Ho-Hyun Park
openaire +1 more source
A brief survey on Capsule Network
2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), 2020Capsule networks(CapsNets) are new kinds of network representation in deep learning. They are proposed to overcome the shortcomings of convolutional neural networks(CNNs). CNNs do not consider the important spatial level correlation between simple and complex objects. Besides, the pooling operations lose too much spatial information.
Ruiyang Shi, Lingfeng Niu
openaire +1 more source