mlsanityData to 14 Oct 2026

Effectiveness of the Recent Advances in Capsule Networks

arXiv 2210.05834 ↗First posted 11 Oct 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Convolutional neural networks (CNNs) have revolutionized the field of deep neural networks. However, recent research has shown that CNNs fail to generalize under various conditions and hence the idea of capsules was introduced in 2011, though the real surge of research started from 2017. In this paper, we present an overview of the recent advances in capsule architecture and routing mechanisms. In addition, we find that the relative focus in recent literature is on modifying routing procedure or architecture as a whole but the study of other finer components, specifically, squash function is wanting. Thus, we also present some new insights regarding the effect of squash functions in performance of the capsule networks. Finally, we conclude by discussing and proposing possible opportunities in the field of capsule networks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 40 references that are in the map. First posted on arXiv 11 Oct 2022.

Builds on

22 of 40 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  5. 2017Squeeze-and-Excitation Networkscited by 4,789
  6. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  7. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  8. 2016Adversarial examples in the physical worldcited by 1,769
  9. 2017Dynamic Routing Between Capsulescited by 689
  10. 2015Recent Advances in Convolutional Neural Networkscited by 360
  11. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 307
  12. 2017Neural Expectation Maximizationcited by 123
10 more
  1. 2015Deep Convolutional Inverse Graphics Networkcited by 121
  2. 2013Stochastic Pooling for Regularization of Deep Convolutional Neural Networkscited by 48
  3. 2018Tree-CNN: A Hierarchical Deep Convolutional Neural Network for Incremental Learningcited by 34
  4. 2018VideoCapsuleNet: A Simplified Network for Action Detectioncited by 30
  5. 2017Capsule Network Performance on Complex Datacited by 22
  6. 2019On the Vulnerability of Capsule Networks to Adversarial Attackscited by 11
  7. 2018CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspacescited by 9
  8. 2018Sparse Unsupervised Capsules Generalize Bettercited by 8
  9. 2018CapsuleGAN: Generative Adversarial Capsule Networkcited by 6
  10. 2015Digging Deep into the layers of CNNs: In Search of How CNNs Achieve View Invariancecited by 3

Built on by

Not cited yet.