Mid Sweden University

miun.sePublications
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
AdAPT: Advertisement detector adaptation under newspaper domain shift with null-based pseudo-labeling
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-). Media Research AB, Östersund.ORCID iD: 0000-0001-6418-2876
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-).ORCID iD: 0000-0001-8661-7578
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-).ORCID iD: 0000-0002-3774-4850
Show others and affiliations
2026 (English)In: Machine Learning with Applications, E-ISSN 2666-8270, Vol. 23, article id 100806Article in journal (Refereed) Published
Abstract [en]

Detecting advertisements in digitized newspapers is a key step in large-scale media analytics and digital archiving. However, variations in layout, typography, and advertisement design across publishers and time periods cause significant domain shifts that reduce the generalization ability of supervised detectors. This paper presents AdAPT, a confidence-guided pseudo-labeling pipeline for unsupervised domain adaptation in advertisement detection. The proposed method leverages both advertisement-free (Null) and advertisement-containing pages from unlabeled target domains to generate reliable pseudo-labels. By retraining a YOLO-based detector using labeled source data combined with filtered pseudo-labeled target samples, AdAPT achieves robust adaptation without requiring manual annotation. Experiments conducted on two unseen newspapers (Adresseavisen and iTromsø) demonstrate that Null-based pseudo-labeling provides the most stable and accurate adaptation, yielding up to 38% error reduction compared to the baseline. The results highlight AdAPT as a simple, scalable, and annotation-efficient solution for maintaining high-performance advertisement detection across diverse newspaper collections. 

Place, publisher, year, edition, pages
Elsevier BV , 2026. Vol. 23, article id 100806
Keywords [en]
Cross-domain advertisement detection, Deep learning, Domain adaptation, Object detection, Pseudo labeling
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:miun:diva-56539DOI: 10.1016/j.mlwa.2025.100806Scopus ID: 2-s2.0-105027856969OAI: oai:DiVA.org:miun-56539DiVA, id: diva2:2034969
Available from: 2026-02-03 Created: 2026-02-03 Last updated: 2026-02-03

Open Access in DiVA

fulltext(2085 kB)69 downloads
File information
File name FULLTEXT01.pdfFile size 2085 kBChecksum SHA-512
35a6d756e5e84aeadd4bd10a2869db8934c1b0eee7ede39b4c4a5c1f5afa86d13653a1a8aed71e1f402e6ccccb916bd14e99debc03fd66a980903c5bc48e1170
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Zakaryapour Sayyad, FaezeSeyed Jalaleddin, MousaviradShallari, IridaO'Nils, Mattias

Search in DiVA

By author/editor
Zakaryapour Sayyad, FaezeSeyed Jalaleddin, MousaviradShallari, IridaO'Nils, Mattias
By organisation
Department of Computer and Electrical Engineering (2023-)
In the same journal
Machine Learning with Applications
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 69 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 5992 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