Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
Visualizing Important Areas for Facial Verification A Deep Learning Evaluation with ArtificialNoise Injection
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology.
2017 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Facial verification is a growing area of research, where heavily trained neural network models obtain superhuman performance on recognizing individuals. However, because of network models' complex nature, it is hard to know what areas of the image are used. This thesis introduces three visualization techniques, to better understand the importance of different facial areas when performing verification. A method for measuring the visualizations' hierarchical correctness was established, evaluating the model's ability to preserve and damage the verification performance, when treated as artificial pixel noise. This is done for two types of networks, which are different in their architecture and their input dimensionality (one taking full color and the other taking grayscale images).

Place, publisher, year, edition, pages
2017. , p. 47
Series
IT ; 17076
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:uu:diva-337660OAI: oai:DiVA.org:uu-337660DiVA, id: diva2:1170504
Supervisors
Examiners
Available from: 2018-01-16 Created: 2018-01-03 Last updated: 2018-01-16Bibliographically approved

Open Access in DiVA

fulltext(13792 kB)91 downloads
File information
File name FULLTEXT01.pdfFile size 13792 kBChecksum SHA-512
036b99440b54b3f047e9d24bcff4030f2450c20be851508c173a858cc6f9854fe870c7ecdaf0d6ffef462d5a97b46e99ef6c190ddc1ba72f2619f16cb0a0fb68
Type fulltextMimetype application/pdf

By organisation
Department of Information Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 91 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: 290 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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