EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

SeGANmentation: Segmentation via GAN-Based Image-to-Image Translation

Maryam Berijanian, Abdi Kusata, Max Fahrenkrug, Amin Sehati, Dirk Colbry

ELCVIA Electronic Letters on Computer Vision and Image Analysis · 05.11.2026 · 25 (3) · 22-44

DOI: 10.5565/rev/elcvia.1995 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ELCVIA Electronic Letters on Computer Vision and Image Analysis, online erschienen am 05.11.2026. Verfasst von Maryam Berijanian und 4 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This research explores the potential of state-of-the-art Generative Adversarial Networks (GANs) for segmentation through image-to-image (I2I) translation. The presented model, seGANmentation, combines convolutional neural networks and vision transformers to generate segmentation labels directly from input images. It aims to reduce manual labeling and enhance segmentation performance using synthetic data. Comparative analysis with U-Net as a benchmark in segmentation, shows U-Net achieving an average of 0.99 in accuracy, Dice Coefficient, and Intersection over Union, while seGANmentation scores 0.90, 0.83, and 0.71, respectively. Although it did not outperform U-Net, it highlights the potential for GAN-based segmentation. This work lays the foundation for employing GANs in this novel approach. This paper's proposed framework could be valuable in data-scarce scenarios, enhance task accuracy with synthetic data augmentation, reduce the need for extensive training pairs by refining GAN-generated labels with off-the-shelf segmentors, and achieve unsupervised segmentation, unlike traditional neural networks. These hypotheses remain to be tested in future studies.

Zitieren

APA

Berijanian, M., Kusata, A., Fahrenkrug, M., Sehati, A., & Colbry, D. (2026). SeGANmentation: Segmentation via GAN-Based Image-to-Image Translation. ELCVIA Electronic Letters on Computer Vision and Image Analysis, 25(3), 22-44. https://doi.org/10.5565/rev/elcvia.1995

Vancouver

Berijanian M, Kusata A, Fahrenkrug M, Sehati A, Colbry D. SeGANmentation: Segmentation via GAN-Based Image-to-Image Translation. ELCVIA Electronic Letters on Computer Vision and Image Analysis. 2026;25(3):22-44. doi:10.5565/rev/elcvia.1995

BibTeX
@article{Berijanian2026,
  author = {Berijanian, Maryam and Kusata, Abdi and Fahrenkrug, Max and Sehati, Amin and Colbry, Dirk},
  title = {SeGANmentation: Segmentation via GAN-Based Image-to-Image Translation},
  journal = {ELCVIA Electronic Letters on Computer Vision and Image Analysis},
  year = {2026},
  volume = {25},
  number = {3},
  pages = {22--44},
  doi = {10.5565/rev/elcvia.1995}
}
Kostenlos starten →