To Örebro University

oru.seÖrebro University Publications
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
Towards Cautious Collective Inference for Object Verification
KU Leuven, ESAT-PSI, iMinds, Leuven, Belgium.
Department of Computer Science, KU Leuven, Leuven, Belgium.ORCID iD: 0000-0002-6860-6303
KU Leuven, ESAT-PSI, iMinds, Leuven, Belgium.
2014 (English)In: IEEE Workshop on Applications of Computer Vision (WACV), IEEE, 2014, p. 269-276Conference paper, Published paper (Refereed)
Abstract [en]

It is by now generally accepted that reasoning about the relationships between objects (and object hypotheses) can improve the accuracy of object detection methods. Relations between objects allow to reject inconsistent hypotheses and reduce the uncertainty of the initial hypotheses. However, most methods to date reason about object relations in a relatively crude way. In this paper we propose an alternative using cautious inference. Building on ideas from Collective Classification, we favor the most confident hypotheses as sources of contextual information and give higher relevance to the object relations observed during training. Additionally, we propose to cluster the pairwise relations into relationships. Our experiments on part of the KITTI data benchmark and the MIT StreetScenes dataset show that both steps improve the performance of relational classifiers.

Place, publisher, year, edition, pages
IEEE, 2014. p. 269-276
Series
IEEE Winter Conference on Applications of Computer Vision, ISSN 2472-6737, E-ISSN 2472-6796
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:oru:diva-92170DOI: 10.1109/WACV.2014.6836089ISI: 000356144800040Scopus ID: 2-s2.0-84904675490ISBN: 9781479949854 (print)OAI: oai:DiVA.org:oru-92170DiVA, id: diva2:1561334
Conference
2014 IEEE Winter Conference on Applications of Computer Vision (WACV 2014), Steamboat Springs, CO, USA, March 24-26, 2014
Available from: 2021-06-07 Created: 2021-06-07 Last updated: 2021-06-07Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

De Raedt, Luc

Search in DiVA

By author/editor
De Raedt, Luc
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 13 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