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
Knowledge is Never Enough: Towards Web Aided Deep Open World Recognition
Sapienza Univ Rome, Rome, Italy.;Fdn Bruno Kessler, Trento, Italy..
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.ORCID iD: 0000-0001-6671-9366
Fdn Bruno Kessler, Trento, Italy.;Univ Trento, Trento, Italy..
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.ORCID iD: 0000-0002-1170-7162
Show others and affiliations
2019 (English)In: 2019 International Conference on Robotics And Automation (ICRA) / [ed] Howard, A Althoefer, K Arai, F Arrichiello, F Caputo, B Castellanos, J Hauser, K Isler, V Kim, J Liu, H Oh, P Santos, V Scaramuzza, D Ude, A Voyles, R Yamane, K Okamura, A, Institute of Electrical and Electronics Engineers (IEEE), 2019, p. 9537-9543, article id 8793803Conference paper, Published paper (Refereed)
Abstract [en]

While today's robots are able to perform sophisticated tasks, they can only act on objects they have been trained to recognize. This is a severe limitation: any robot will inevitably see new objects in unconstrained settings, and thus will always have visual knowledge gaps. However, standard visual modules are usually built on a limited set of classes and are based on the strong prior that an object must belong to one of those classes. Identifying whether an instance does not belong to the set of known categories (i.e. open set recognition), only partially tackles this problem, as a truly autonomous agent should be able not only to detect what it does not know, but also to extend dynamically its knowledge about the world. We contribute to this challenge with a deep learning architecture that can dynamically update its known classes in an end-to-end fashion. The proposed deep network, based on a deep extension of a non-parametric model, detects whether a perceived object belongs to the set of categories known by the system and learns it without the need to retrain the whole system from scratch. Annotated images about the new category can be provided by an 'oracle' (i.e. human supervision), or by autonomous mining of the Web. Experiments on two different databases and on a robot platform demonstrate the promise of our approach.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2019. p. 9537-9543, article id 8793803
Series
IEEE International Conference on Robotics and Automation ICRA, ISSN 1050-4729
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-265459DOI: 10.1109/ICRA.2019.8793803ISI: 000494942306142Scopus ID: 2-s2.0-85071460733ISBN: 978-1-5386-6026-3 (print)OAI: oai:DiVA.org:kth-265459DiVA, id: diva2:1380298
Conference
2019 International Conference on Robotics and Automation, ICRA 2019; Palais des Congres de Montreal, Montreal; Canada; 20-24 May 2019
Note

QC 20191218

Available from: 2019-12-18 Created: 2019-12-18 Last updated: 2019-12-20Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Jensfelt, Patric

Search in DiVA

By author/editor
Karaoguz, HakanJensfelt, Patric
By organisation
Robotics, Perception and Learning, RPL
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 3 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