EUVIMEDEUVIMED entdecken
Crossref

Probabilistic Graphical Models Meet Deep Learning for Semantic Segmentation: Mathematical connections and recent developments

Martina Pastorino, Gabriele Moser, Sebastiano B. Serpico, Josiane Zerubia

IEEE Signal Processing Magazine · 2026-03 · 43 (2) · 51-63

DOI: 10.1109/msp.2025.3648958 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Magazine, 2026-03. Verfasst von Martina Pastorino und 3 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic segmentation, also known as spatially dense image classification, plays a crucial role in image analysis, bridging the fields of image processing and machine learning. It has wide applications, ranging from land cover mapping in Earth observation to medical diagnostics using biomedical images, fault detection in industrial imagery, and so on. This article focuses on the mathematical connections between two pivotal families of methodological approaches—probabilistic graphical models (PGMs) and deep learning (DL)—and explores the potential of their integration for semantic segmentation tasks. After providing a comprehensive overview of state-of-the-art techniques from both families, the article highlights recent developments that combine these approaches, either through theoretical equivalence or direct integration. Examples of results are provided for renowned benchmark datasets in computer vision and remote sensing, and the article concludes with a discussion of promising future research directions.

Zitieren

APA

Pastorino, M., Moser, G., Serpico, S. B., & Zerubia, J. (2026). Probabilistic Graphical Models Meet Deep Learning for Semantic Segmentation: Mathematical connections and recent developments. IEEE Signal Processing Magazine, 43(2), 51-63. https://doi.org/10.1109/msp.2025.3648958

Vancouver

Pastorino M, Moser G, Serpico SB, Zerubia J. Probabilistic Graphical Models Meet Deep Learning for Semantic Segmentation: Mathematical connections and recent developments. IEEE Signal Processing Magazine. 2026;43(2):51-63. doi:10.1109/msp.2025.3648958

BibTeX
@article{Pastorino2026,
  author = {Pastorino, Martina and Moser, Gabriele and Serpico, Sebastiano B. and Zerubia, Josiane},
  title = {Probabilistic Graphical Models Meet Deep Learning for Semantic Segmentation: Mathematical connections and recent developments},
  journal = {IEEE Signal Processing Magazine},
  year = {2026},
  volume = {43},
  number = {2},
  pages = {51--63},
  doi = {10.1109/msp.2025.3648958}
}
Kostenlos starten →