Deep multi-prototype capsule networks
- URL: http://arxiv.org/abs/2404.15445v1
- Date: Tue, 23 Apr 2024 18:37:37 GMT
- Title: Deep multi-prototype capsule networks
- Authors: Saeid Abbassi, Kamaledin Ghiasi-Shirazi, Ahad Harati,
- Abstract summary: Capsule networks are a type of neural network that identify image parts and form the instantiation parameters of a whole hierarchically.
This paper presents a multi-prototype architecture for guiding capsule networks to represent the variations in the image parts.
The experimental results on MNIST, SVHN, C-Cube, CEDAR, MCYT, and UTSig datasets reveal that the proposed model outperforms others regarding image classification accuracy.
- Score: 0.3823356975862005
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Capsule networks are a type of neural network that identify image parts and form the instantiation parameters of a whole hierarchically. The goal behind the network is to perform an inverse computer graphics task, and the network parameters are the mapping weights that transform parts into a whole. The trainability of capsule networks in complex data with high intra-class or intra-part variation is challenging. This paper presents a multi-prototype architecture for guiding capsule networks to represent the variations in the image parts. To this end, instead of considering a single capsule for each class and part, the proposed method employs several capsules (co-group capsules), capturing multiple prototypes of an object. In the final layer, co-group capsules compete, and their soft output is considered the target for a competitive cross-entropy loss. Moreover, in the middle layers, the most active capsules map to the next layer with a shared weight among the co-groups. Consequently, due to the reduction in parameters, implicit weight-sharing makes it possible to have more deep capsule network layers. The experimental results on MNIST, SVHN, C-Cube, CEDAR, MCYT, and UTSig datasets reveal that the proposed model outperforms others regarding image classification accuracy.
Related papers
- Learning with Capsules: A Survey [73.31150426300198]
Capsule networks were proposed as an alternative approach to Convolutional Neural Networks (CNNs) for learning object-centric representations.
Unlike CNNs, capsule networks are designed to explicitly model part-whole hierarchical relationships.
arXiv Detail & Related papers (2022-06-06T15:05:36Z) - HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing
Capsule Network [76.92310948325847]
We propose a Hierarchical Parsing Capsule Network (HP-Capsule) for unsupervised face subpart-part discovery.
HP-Capsule extends the application of capsule networks from digits to human faces and takes a step forward to show how the neural networks understand objects without human intervention.
arXiv Detail & Related papers (2022-03-21T01:39:41Z) - Augmenting Convolutional networks with attention-based aggregation [55.97184767391253]
We show how to augment any convolutional network with an attention-based global map to achieve non-local reasoning.
We plug this learned aggregation layer with a simplistic patch-based convolutional network parametrized by 2 parameters (width and depth)
It yields surprisingly competitive trade-offs between accuracy and complexity, in particular in terms of memory consumption.
arXiv Detail & Related papers (2021-12-27T14:05:41Z) - Routing with Self-Attention for Multimodal Capsule Networks [108.85007719132618]
We present a new multimodal capsule network that allows us to leverage the strength of capsules in the context of a multimodal learning framework.
To adapt the capsules to large-scale input data, we propose a novel routing by self-attention mechanism that selects relevant capsules.
This allows not only for robust training with noisy video data, but also to scale up the size of the capsule network compared to traditional routing methods.
arXiv Detail & Related papers (2021-12-01T19:01:26Z) - Capsule networks with non-iterative cluster routing [2.8935588665357077]
In existing routing procedures, capsules produce predictions (termed votes) for capsules of the next layer.
In the proposed cluster routing, capsules produce vote clusters instead of individual votes for next-layer capsules.
The proposed capsule networks achieve the best accuracy on the Fashion-MNIST and SVHN datasets with fewer parameters.
arXiv Detail & Related papers (2021-09-19T20:14:22Z) - ASPCNet: A Deep Adaptive Spatial Pattern Capsule Network for
Hyperspectral Image Classification [47.541691093680406]
This paper proposes an adaptive spatial pattern capsule network (ASPCNet) architecture.
It can rotate the sampling location of convolutional kernels on the basis of an enlarged receptive field.
Experiments on three public datasets demonstrate that ASPCNet can yield competitive performance with higher accuracies than state-of-the-art methods.
arXiv Detail & Related papers (2021-04-25T07:10:55Z) - Training Deep Capsule Networks with Residual Connections [0.0]
Capsule networks are a type of neural network that have recently gained increased popularity.
They consist of groups of neurons, called capsules, which encode properties of objects or object parts.
Most capsule network implementations use two to three capsule layers, which limits their applicability as expressivity grows exponentially with depth.
We propose a methodology to train deeper capsule networks using residual connections, which is evaluated on four datasets and three different routing algorithms.
Our experimental results show that in fact, performance increases when training deeper capsule networks.
arXiv Detail & Related papers (2021-04-15T11:42:44Z) - Deformable Capsules for Object Detection [3.702343116848637]
We introduce a new family of capsule networks, deformable capsules (textitDeformCaps), to address a very important problem in computer vision: object detection.
We demonstrate that the proposed methods efficiently scale up to create the first-ever capsule network for object detection in the literature.
arXiv Detail & Related papers (2021-04-11T15:36:30Z) - Subspace Capsule Network [85.69796543499021]
SubSpace Capsule Network (SCN) exploits the idea of capsule networks to model possible variations in the appearance or implicitly defined properties of an entity.
SCN can be applied to both discriminative and generative models without incurring computational overhead compared to CNN during test time.
arXiv Detail & Related papers (2020-02-07T17:51:56Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.