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
Deep Perceptual Similarity is Adaptable to Ambiguous Contexts
Dept. of Computing Science, Umeå University.
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.ORCID iD: 0000-0001-5662-825X
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.ORCID iD: 0000-0003-4029-6574
2024 (English)In: Proceedings of Machine Learning Research, PMLR: Volume 233: Northern Lights Deep Learning Conference, 9-11 January 2024, UiT The Arctic University, Tromsø, Norway / [ed] Tetiana Lutchyn; Adin Ramirez Rivera; Benjamin Ricaud, Proceedings of Machine Learning Research , 2024, p. 212-219Conference paper, Published paper (Refereed)
Abstract [en]

This work examines the adaptability of Deep Perceptual Similarity (DPS) metrics to context beyond those that align with average human perception and contexts in which the standard metrics have been shown to perform well. Prior works have shown that DPS metrics are good at estimating human perception of similarity, so-called perceptual similarity. However, it remains unknown whether such metrics can be adapted to other contexts. In this work, DPS metrics are evaluated for their adaptability to different contradictory similarity contexts. Such contexts are created by randomly ranking six image distortions. Metrics are adapted to consider distortions more or less disruptive to similarity depending on their place in the random rankings. This is done by training pretrained CNNs to measure similarity according to given contexts. The adapted metrics are also evaluated on a perceptual similarity dataset to evaluate whether adapting to a ranking affects their prior performance. The findings show that DPS metrics can be adapted with high performance. While the adapted metrics have difficulties with the same contexts as baselines, performance is improved in 99% of cases. Finally, it is shown that the adaption is not significantly detrimental to prior performance on perceptual similarity. The implementation of this work is available online.

Place, publisher, year, edition, pages
Proceedings of Machine Learning Research , 2024. p. 212-219
Series
Proceedings of Machine Learning Research, E-ISSN 2640-3498 ; 233
National Category
Computer and Information Sciences Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Machine Learning
Identifiers
URN: urn:nbn:se:ltu:diva-105093Scopus ID: 2-s2.0-85189301791OAI: oai:DiVA.org:ltu-105093DiVA, id: diva2:1851570
Conference
5th Northern Lights Deep Learning Conference (NLDL 2024), Tromsø, Norway, January 9-11, 2024
Note

Full text license: CC BY 4.0; 

Available from: 2024-04-15 Created: 2024-04-15 Last updated: 2024-04-15Bibliographically approved

Open Access in DiVA

fulltext(1469 kB)44 downloads
File information
File name FULLTEXT01.pdfFile size 1469 kBChecksum SHA-512
3659fc9ab055d9bf0d581200622a4ca636b31f9c1774c762396aaeb6d00dfc8146a1148bac55c82a5a8fc9632df00e6814181be752911081b02b3fb3040bced9
Type fulltextMimetype application/pdf

Other links

ScopusPublisher's full text

Authority records

Sandin, FredrikLiwicki, Marcus

Search in DiVA

By author/editor
Sandin, FredrikLiwicki, Marcus
By organisation
Embedded Internet Systems Lab
Computer and Information SciencesElectrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 44 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: 369 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