OnlyCaps-Net, a Capsule only Based Neural Network for 2D and 3D Semantic Segmentation

Savinien Bonheur*, Franz Thaler, Michael Pienn, Horst Olschewski, Horst Bischof, Martin Urschler

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

Since their introduction by Sabour et al., capsule networks have been extended to 2D semantic segmentation with the introduction of convolutional capsules. While extended further to 3D semantic segmentation when mixed with Convolutional Neural Networks (CNNs), no capsule-only network (to the best of our knowledge) has been able to reach CNNs’ accuracy on multilabel segmentation tasks. In this work, we propose OnlyCaps-Net, the first competitive capsule-only network for 2D and 3D multi-label semantic segmentation. OnlyCaps-Net improves both capsules’ accuracy and inference speed by replacing Sabour et al. squashing with the introduction of two novel squashing functions, i.e. softsquash or unitsquash, and the iterative routing with a new parameter free single pass routing, i.e. unit routing. Additionally, OnlyCaps-Net introduces a new parameter efficient convolutional capsule type, i.e. depthwise separable convolutional capsule.

Original languageEnglish
Title of host publicationMedical Image Computing and Computer Assisted Intervention – MICCAI 2022 - 25th International Conference, Proceedings
EditorsLinwei Wang, Qi Dou, P. Thomas Fletcher, Stefanie Speidel, Shuo Li
PublisherSpringer Science and Business Media Deutschland GmbH
Pages340-349
Number of pages10
ISBN (Print)9783031164422
DOIs
Publication statusPublished - 2022
Event25th International Conference on Medical Image Computing and Computer Assisted Intervention: MICCAI 2022 - Singapur, Singapore
Duration: 18 Sept 202222 Sept 2022

Publication series

NameLecture Notes in Computer Science
Volume13435
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference25th International Conference on Medical Image Computing and Computer Assisted Intervention
Abbreviated titleMICCAI 2022
Country/TerritorySingapore
CitySingapur
Period18/09/2222/09/22

Keywords

  • 2D
  • 3D
  • Capsule networks
  • Convolutional Neural Networks
  • Multi-label
  • Semantic segmentation

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint

Dive into the research topics of 'OnlyCaps-Net, a Capsule only Based Neural Network for 2D and 3D Semantic Segmentation'. Together they form a unique fingerprint.

Cite this