Pushing the Limits of Capsule Networks

• URL: http://arxiv.org/abs/2103.08074v1
• Date: Mon, 15 Mar 2021 00:30:34 GMT
• Title: Pushing the Limits of Capsule Networks
• Authors: Prem Nair, Rohan Doshi, Stefan Keselj
• Abstract summary: Convolutional neural networks do not explicitly maintain a representation of the locations of the features relative to each other. A team at Google Brain recently made news with an attempt to fix this problem: Capsule Networks. We want to stress test CapsNet in various incremental ways to better understand their performance and expressiveness.
• Score: 1.8231854497751137
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Convolutional neural networks use pooling and other downscaling operations to maintain translational invariance for detection of features, but in their architecture they do not explicitly maintain a representation of the locations of the features relative to each other. This means they do not represent two instances of the same object in different orientations the same way, like humans do, and so training them often requires extensive data augmentation and exceedingly deep networks. A team at Google Brain recently made news with an attempt to fix this problem: Capsule Networks. While a normal CNN works with scalar outputs representing feature presence, a CapsNet works with vector outputs representing entity presence. We want to stress test CapsNet in various incremental ways to better understand their performance and expressiveness. In broad terms, the goals of our investigation are: (1) test CapsNets on datasets that are like MNIST but harder in a specific way, and (2) explore the internal embedding space and sources of error for CapsNets.

Related papers

• RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attacks [11.302789770501303]
  Capsule Networks (CapsNets) are able to hierarchically preserve the pose relationships between multiple objects for image classification tasks. In this paper, we evaluate different factors affecting the robustness of CapsNets, compared to traditional Conal Neural Networks (CNNs)
  arXiv  Detail & Related papers  (2023-04-08T09:58:35Z)
• Dynamic Graph Message Passing Networks for Visual Recognition [112.49513303433606]
  Modelling long-range dependencies is critical for scene understanding tasks in computer vision. A fully-connected graph is beneficial for such modelling, but its computational overhead is prohibitive. We propose a dynamic graph message passing network, that significantly reduces the computational complexity.
  arXiv  Detail & Related papers  (2022-09-20T14:41:37Z)
• SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation [65.4396959244269]
  The paper tackles the challenge by designing a general framework to construct 3D learning architectures. The proposed approach can be applied to general backbones like PointNet and DGCNN. Experiments on ModelNet40, ShapeNet, and the real-world dataset ScanObjectNN, demonstrated that the method achieves a great trade-off between efficiency, rotation, and accuracy.
  arXiv  Detail & Related papers  (2022-09-13T12:12:19Z)
• CapsNet for Medical Image Segmentation [8.612958742534673]
  Convolutional Neural Networks (CNNs) have been successful in solving tasks in computer vision. CNNs are sensitive to rotation and affine transformation and their success relies on huge-scale labeled datasets. CapsNet is a new architecture that has achieved better robustness in representation learning.
  arXiv  Detail & Related papers  (2022-03-16T21:15:07Z)
• Spiking CapsNet: A Spiking Neural Network With A Biologically Plausible Routing Rule Between Capsules [9.658836348699161]
  Spiking neural network (SNN) has attracted much attention due to their powerful-temporal information representation ability. CapsNet does well in assembling and coupling different levels. We propose Spiking CapsNet by introducing the capsules into the modelling of neural networks.
  arXiv  Detail & Related papers  (2021-11-15T14:23:15Z)
• Parallel Capsule Networks for Classification of White Blood Cells [1.5749416770494706]
  Capsule Networks (CapsNets) is a machine learning architecture proposed to overcome some of the shortcomings of convolutional neural networks (CNNs) We present a new architecture, parallel CapsNets, which exploits the concept of branching the network to isolate certain capsules.
  arXiv  Detail & Related papers  (2021-08-05T14:30:44Z)
• Learning distinct features helps, provably [98.78384185493624]
  We study the diversity of the features learned by a two-layer neural network trained with the least squares loss. We measure the diversity by the average $L$-distance between the hidden-layer features.
  arXiv  Detail & Related papers  (2021-06-10T19:14:45Z)
• Leveraging Sparse Linear Layers for Debuggable Deep Networks [86.94586860037049]
  We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. The resulting sparse explanations can help to identify spurious correlations, explain misclassifications, and diagnose model biases in vision and language tasks.
  arXiv  Detail & Related papers  (2021-05-11T08:15:25Z)
• Interpretable Graph Capsule Networks for Object Recognition [17.62514568986647]
  We propose interpretable Graph Capsule Networks (GraCapsNets), where we replace the routing part with a multi-head attention-based Graph Pooling approach. GraCapsNets achieve better classification performance with fewer parameters and better adversarial robustness, when compared to CapsNets.
  arXiv  Detail & Related papers  (2020-12-03T03:18:00Z)
• iCapsNets: Towards Interpretable Capsule Networks for Text Classification [95.31786902390438]
  Traditional machine learning methods are easy to interpret but have low accuracies. We propose interpretable capsule networks (iCapsNets) to bridge this gap. iCapsNets can be interpreted both locally and globally.
  arXiv  Detail & Related papers  (2020-05-16T04:11:44Z)
• 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.