liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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
Likelihood-free Out-of-Distribution Detection with Invertible Generative Models
Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0001-7411-2177
Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering.
2021 (English)In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI 2021), International Joint Conferences on Artifical Intelligence (IJCAI) , 2021, p. 2119-2125Conference paper, Published paper (Refereed)
Abstract [en]

Likelihood of generative models has been used traditionally as a score to detect atypical (Out-of-Distribution, OOD) inputs. However, several recent studies have found this approach to be highly unreliable, even with invertible generative models, where computing the likelihood is feasible. In this paper, we present a different framework for generative model--based OOD detection that employs the model in constructing a new representation space, instead of using it directly in computing typicality scores, where it is emphasized that the score function should be interpretable as the similarity between the input and training data in the new space. In practice, with a focus on invertible models, we propose to extract low-dimensional features (statistics) based on the model encoder and complexity of input images, and then use a One-Class SVM to score the data. Contrary to recently proposed OOD detection methods for generative models, our method does not require computing likelihood values. Consequently, it is much faster when using invertible models with iteratively approximated likelihood (e.g. iResNet), while it still has a performance competitive with other related methods

Place, publisher, year, edition, pages
International Joint Conferences on Artifical Intelligence (IJCAI) , 2021. p. 2119-2125
Series
Proceedings of the International Joint Conference on Artificial Intelligence, ISSN 1045-0823
Keywords [en]
Deep Learning, Anomaly/Outlier Detection, Uncertainty Representations
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:liu:diva-188936DOI: 10.24963/ijcai.2021/292ISI: 001202335502027Scopus ID: 2-s2.0-85125461759ISBN: 9780999241196 (electronic)OAI: oai:DiVA.org:liu-188936DiVA, id: diva2:1700681
Conference
International Joint Conference on Artificial Intelligence (IJCAI), 19-26 August, 2021
Available from: 2022-10-03 Created: 2022-10-03 Last updated: 2024-09-23Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Ahmadian, AmirhosseinLindsten, Fredrik

Search in DiVA

By author/editor
Ahmadian, AmirhosseinLindsten, Fredrik
By organisation
The Division of Statistics and Machine LearningFaculty of Science & Engineering
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 195 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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