Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
CapsNet Comprehension of Objects in Different Rotational Views: A comparative study of capsule and convolutional networks
KTH, School of Electrical Engineering and Computer Science (EECS), Software and Computer systems, SCS.
2018 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Capsule network (CapsNet) is a new and promising approach to computer vision. In the small amount of research published so far, it has shown to be good at generalizing complex objects and perform well even when the images are skewed or the objects are seen from unfamiliar viewpoints. This thesis further tests this ability of CapsNetby comparing it to convolutional networks (ConvNets) on the task to understand images of clothing in different rotational views. Even though the ConvNets have a higher classification accuracy than CapsNets, the results indicate that CapsNets are better at understanding the clothes when viewed in different rotational views.

Abstract [sv]

Capsule network (CapsNet) är en ny typ av neuralt nätverk för datorseende, som framförallt presterar bra även då bilderna är förvrängda eller sedda från obekanta vinklar. Den här uppsatsen testar CapsNets förmåga att förstå klädesobjekt sedda ur olika synviklar genom att göra en jämförelse med ConvNets. Resultaten visar att, trots att ConvNets har en högre exakthet i sin klassificering, är CapsNets bättre på att förstå kläderna sedda från olika synvinklar.

Place, publisher, year, edition, pages
2018.
Series
TRITA-EECS-EX ; 2018:395
Keywords [en]
capsnet, convolutional, network, capsule, neural, clothing, clothes, sellpy, rotation, rotational, views
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-231898OAI: oai:DiVA.org:kth-231898DiVA, id: diva2:1230671
External cooperation
Sellpy
Educational program
Master of Science in Engineering - Computer Science and Technology
Supervisors
Examiners
Available from: 2018-08-24 Created: 2018-07-04 Last updated: 2018-08-24Bibliographically approved

Open Access in DiVA

fulltext(1114 kB)177 downloads
File information
File name FULLTEXT01.pdfFile size 1114 kBChecksum SHA-512
3f21baeb4ab3539d5d2a313c0c91f43f7337ff5c135a09bb51993e4f6185bec533260cab3038e88cfe6c3b5f619d0ad866a5907b75c5f7a451a79fff6f33b188
Type fulltextMimetype application/pdf

By organisation
Software and Computer systems, SCS
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 177 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 901 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf