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
Visual state estimation in unseen environments through domain adaptation and metric learning
Örebro University, Örebro, Sweden. (Autonomous Mobile Manipulation Lab)
Örebro University, School of Science and Technology. (Autonomous Mobile Manipulation Lab)ORCID iD: 0000-0003-3958-6179
Örebro University, School of Science and Technology. (Autonomous Mobile Manipulation Lab)ORCID iD: 0000-0002-6013-4874
2022 (English)In: Frontiers in Robotics and AI, E-ISSN 2296-9144, Vol. 9, article id 833173Article in journal (Refereed) Published
Abstract [en]

In robotics, deep learning models are used in many visual perception applications, including the tracking, detection and pose estimation of robotic manipulators. The state of the art methods however are conditioned on the availability of annotated training data, which may in practice be costly or even impossible to collect. Domain augmentation is one popular method to improve generalization to out-of-domain data by extending the training data set with predefined sources of variation, unrelated to the primary task. While this typically results in better performance on the target domain, it is not always clear that the trained models are capable to accurately separate the signals relevant to solving the task (e.g., appearance of an object of interest) from those associated with differences between the domains (e.g., lighting conditions). In this work we propose to improve the generalization capabilities of models trained with domain augmentation by formulating a secondary structured metric-space learning objective. We concentrate on one particularly challenging domain transfer task-visual state estimation for an articulated underground mining machine-and demonstrate the benefits of imposing structure on the encoding space. Our results indicate that the proposed method has the potential to transfer feature embeddings learned on the source domain, through a suitably designed augmentation procedure, and on to an unseen target domain.

Place, publisher, year, edition, pages
Frontiers Media S.A., 2022. Vol. 9, article id 833173
Keywords [en]
articulated pose estimation, deep metric learning, domain augmentation, joint state estimation, triplet loss
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:oru:diva-101091DOI: 10.3389/frobt.2022.833173ISI: 000849778200001PubMedID: 36059568OAI: oai:DiVA.org:oru-101091DiVA, id: diva2:1693298
Funder
Vinnova, 2017-02205Available from: 2022-09-06 Created: 2022-09-06 Last updated: 2022-09-13Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMed

Authority records

Stork, Johannes A.Stoyanov, Todor

Search in DiVA

By author/editor
Stork, Johannes A.Stoyanov, Todor
By organisation
School of Science and Technology
In the same journal
Frontiers in Robotics and AI
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 16 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