EUVIMEDScopri EUVIMED
Open access · CC BY 4.0

Weighting Strategies for Tabular and Image Data Classification

Marina Lukashevich, Sergei Bairak

IET Image Processing · 2026-01 · 20 (1)

DOI: 10.1049/ipr2.70365 ↗

At a glance

Journal article in IET Image Processing, published online on 2026-05-06. Written by Marina Lukashevich and 1 co-authors. 31 references. The full text is freely available (open access, CC BY 4.0). Funded by: Belarusian Republican Foundation for Fundamental Research.

AbstractDati bibliograficiCiteRelated studies

Abstract (original language)

Class imbalance is a significant problem in classification tasks for various data types, such as tabular data and images. Data imbalance can lead to biased models that fail to correctly identify minor classes. This paper presents the results of experimental studies of weighting methods for classical ensemble algorithms applied to tabular data, as well as for neural networks used for image classification. The results demonstrate that the inverse frequency method, despite being widely adopted, does not consistently yield optimal classification performance. General recommendations for addressing class imbalance in both tabular and image data are provided. The findings suggest that alternative weighting strategies beyond standard implementations warrant exploration and should be integrated into hyperparameter optimisation.

Funding

  • Belarusian Republican Foundation for Fundamental Research

Cite

APA

Lukashevich, M., & Bairak, S. (2026). Weighting Strategies for Tabular and Image Data Classification. IET Image Processing, 20(1). https://doi.org/10.1049/ipr2.70365

Vancouver

Lukashevich M, Bairak S. Weighting Strategies for Tabular and Image Data Classification. IET Image Processing. 2026;20(1). doi:10.1049/ipr2.70365

BibTeX
@article{Lukashevich2026,
  author = {Lukashevich, Marina and Bairak, Sergei},
  title = {Weighting Strategies for Tabular and Image Data Classification},
  journal = {IET Image Processing},
  year = {2026},
  volume = {20},
  number = {1},
  doi = {10.1049/ipr2.70365}
}
Start for free →