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
Mask-Aware Semi-Supervised Object Detection in Floor Plans
Department of Computer Science, Technical University of Kaiserslautern, Kaiserslautern, 67663, Germany; Department of Computer Science, Mindgarage, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany; German Research Institute for Artificial Intelligence (DFKI), Kaiserslautern, 67663, Germany.ORCID iD: 0000-0002-7052-979X
Department of Computer Science, Technical University of Kaiserslautern, Kaiserslautern, 67663, Germany; Department of Computer Science, Mindgarage, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany; German Research Institute for Artificial Intelligence (DFKI), Kaiserslautern, 67663, Germany.ORCID iD: 0000-0003-0456-6493
German Research Institute for Artificial Intelligence (DFKI), Kaiserslautern, 67663, Germany.
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.ORCID iD: 0000-0003-4029-6574
Show others and affiliations
2022 (English)In: Applied Sciences, E-ISSN 2076-3417, Vol. 12, no 19, article id 9398Article in journal (Refereed) Published
Abstract [en]

Research has been growing on object detection using semi-supervised methods in past few years. We examine the intersection of these two areas for floor-plan objects to promote the research objective of detecting more accurate objects with less labeled data. The floor-plan objects include different furniture items with multiple types of the same class, and this high inter-class similarity impacts the performance of prior methods. In this paper, we present Mask R-CNN-based semi-supervised approach that provides pixel-to-pixel alignment to generate individual annotation masks for each class to mine the inter-class similarity. The semi-supervised approach has a student–teacher network that pulls information from the teacher network and feeds it to the student network. The teacher network uses unlabeled data to form pseudo-boxes, and the student network uses both label data with the pseudo boxes and labeled data as the ground truth for training. It learns representations of furniture items by combining labeled and label data. On the Mask R-CNN detector with ResNet-101 backbone network, the proposed approach achieves a mAP of 98.8%, 99.7%, and 99.8% with only 1%, 5% and 10% labeled data, respectively. Our experiment affirms the efficiency of the proposed approach, as it outperforms the previous semi-supervised approaches using only 1% of the labels.

Place, publisher, year, edition, pages
MDPI , 2022. Vol. 12, no 19, article id 9398
Keywords [en]
computer vision, floor-plan images, Mask R-CNN, object detection, semi-supervised learning
National Category
Computer Sciences
Research subject
Machine Learning
Identifiers
URN: urn:nbn:se:ltu:diva-93723DOI: 10.3390/app12199398ISI: 000866834200001Scopus ID: 2-s2.0-85139925595OAI: oai:DiVA.org:ltu-93723DiVA, id: diva2:1706541
Projects
INFINITY
Funder
EU, Horizon 2020, INFINITY 883293
Note

Validerad;2022;Nivå 2;2022-10-26 (hanlid)

Available from: 2022-10-26 Created: 2022-10-26 Last updated: 2022-11-08Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Liwicki, Marcus

Search in DiVA

By author/editor
Shehzadi, TahiraHashmi, Khurram AzeemLiwicki, MarcusAfzal, Muhammad Zeshan
By organisation
Embedded Internet Systems Lab
In the same journal
Applied Sciences
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 41 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