EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semantic Segmentation by Semantic Proportions

Halil Ibrahim Aysel iD, Xiaohao Cai, Adam Prugel-Bennett

Sensors · 19.08.2026 · 26 (16) · 5262

DOI: 10.3390/s26165262 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.08.2026. Verfasst von Halil Ibrahim Aysel und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ, UK. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic segmentation is a critical task in computer vision aiming to identify and classify individual pixels in an image, with numerous applications, for example, in autonomous driving and medical image analysis. However, semantic segmentation can be highly challenging, particularly due to the need for large amounts of annotated data. Annotating images is a time-consuming and costly process, often requiring expert knowledge and significant effort; moreover, saving the annotated images could dramatically increase the storage space. In this paper, we propose a novel approach for semantic segmentation, requiring only rough information about the proportions of individual semantic classes, hereafter referred to as semantic proportions (SPs), rather than the necessity of ground-truth segmentation maps. This greatly simplifies the data annotation process and thus will significantly reduce the annotation time, cost and storage space, opening up new possibilities for semantic segmentation tasks where obtaining the full ground-truth segmentation maps may not be feasible or practical. Our proposed method of utilising semantic proportions can (i) further be utilised as a booster in the presence of ground-truth segmentation maps to gain performance without extra data and model complexity, and (ii) also be seen as a parameter-free plug-and-play module, which can be attached to existing deep neural networks designed for semantic segmentation. Extensive experimental results demonstrate the good performance of our method compared to benchmark methods that rely on ground-truth segmentation maps. Utilising semantic proportions suggested in this work offers a promising direction for future semantic segmentation research.

Schlagwörter

Stichwörter der Autor:innen

plug and playsemantic proportionssemantic segmentationweakly supervised learning

Autor:innen und Institutionen

  • School of Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ, UK.

ORCID-Profile: Halil Ibrahim Aysel

Zitieren

APA

Aysel, H. I., Cai, X., & Prugel-Bennett, A. (2026). Semantic Segmentation by Semantic Proportions. Sensors, 26(16), 5262. https://doi.org/10.3390/s26165262

Vancouver

Aysel HI, Cai X, Prugel-Bennett A. Semantic Segmentation by Semantic Proportions. Sensors. 2026;26(16):5262. doi:10.3390/s26165262

BibTeX
@article{Aysel2026,
  author = {Aysel, Halil Ibrahim and Cai, Xiaohao and Prugel-Bennett, Adam},
  title = {Semantic Segmentation by Semantic Proportions},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {16},
  pages = {5262},
  doi = {10.3390/s26165262}
}
Kostenlos starten →