Malmö 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
Hierarchical Transfer Multi-task Learning Approach for Scene Classification
Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).ORCID iD: 0000-0002-3797-4605
Faculty of Electrical and Computer Engineering, Qom University of Technology, Qom, Iran.
Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).ORCID iD: 0000-0002-9464-7010
Axis Communications AB, Lund, Sweden.
Show others and affiliations
2024 (English)In: Pattern Recognition: 27th International Conference, ICPR 2024, Kolkata, India, December 1–5, 2024, Proceedings, Part I, Springer, 2024, p. 231-248Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents a novel Hierarchical Transfer and Multi-task Learning (HTMTL) approach designed to substantially improve the performance of scene classification networks by leveraging the collective influence of diverse scene types. HTMTL is distinguished by its ability to capture the interaction between various scene types, recognizing how context information from one scene category can enhance the classification performance of another. Our method, when applied to the Places365 dataset, demonstrates a significant improvement in the network’s ability to accurately identify scene types. By exploiting these inter-scene interactions, HTMTL significantly enhances scene classification performance, making it a potent tool for advancing scene understanding and classification. Additionally, this study explores the contribution of individual tasks and task groupings on the performance of other tasks. To further validate the generality of HTMTL, we applied it to the Cityscapes dataset, where the results also show promise. This indicates the broad applicability and effectiveness of our approach across different datasets and scene types.

Place, publisher, year, edition, pages
Springer, 2024. p. 231-248
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 15301
Keywords [en]
Multi-task Learning; Scene Classification; Transfer Learning
National Category
Natural Language Processing
Identifiers
URN: urn:nbn:se:mau:diva-72852DOI: 10.1007/978-3-031-78107-0_15Scopus ID: 2-s2.0-85211958209ISBN: 978-3-031-78106-3 (print)ISBN: 978-3-031-78107-0 (electronic)OAI: oai:DiVA.org:mau-72852DiVA, id: diva2:1923100
Conference
27th International Conference, ICPR 2024, Kolkata, India, December 1–5, 2024
Available from: 2024-12-20 Created: 2024-12-20 Last updated: 2025-02-07Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Khoshkangini, RezaJamali, MahtabMihailescu, Radu-CasianDavidsson, Paul

Search in DiVA

By author/editor
Khoshkangini, RezaJamali, MahtabMihailescu, Radu-CasianDavidsson, Paul
By organisation
Department of Computer Science and Media Technology (DVMT)Internet of Things and People (IOTAP)
Natural Language Processing

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 38 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