EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HDVS: semi-supervised semantic segmentation via heterogeneous dual-branch voting supervision

Yongqi Shan, Yunzhi Zhuge, Huchuan Lu

Visual Intelligence · 2026-12 · 4 (1)

DOI: 10.1007/s44267-026-00107-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Visual Intelligence, online erschienen am 03.02.2026. Verfasst von Yongqi Shan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: other.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semi-supervised semantic segmentation, which aims to utilize large volumes of unlabeled images to achieve accurate segmentation results with fewer human annotations, has attracted increasing attention. Prior methods were primarily based on the assumption that the pseudo-labels generated by each branch were sufficiently reliable to supervise the remaining branches. However, there is a concern that the errors in pseudo-labels could accumulate during co-training, potentially resulting in suboptimal performance. To this end, we present a novel framework called heterogeneous dual-branch voting supervision (HDVS), which is designed to enhance the reliability of pseudo-labels and mitigate the issues arising from pseudo-labeling. Specifically, based on the cross-supervision framework, we introduce a voting mechanism that correlates pseudo-labels from heterogeneous branches to produce pseudo-labels with enhanced reliability. Concurrently, we employ a feature communication module to introduce perturbations at the feature level in each branch to maximize prediction diversity across the dual branches while maintaining convergence. Comprehensive evaluations of the proposed HDVS on two benchmark datasets (PASCAL VOC 2012 and Cityscapes) demonstrate its superiority to the state-of-the-art approaches.

Förderung

  • other

Zitieren

APA

Shan, Y., Zhuge, Y., & Lu, H. (2026). HDVS: semi-supervised semantic segmentation via heterogeneous dual-branch voting supervision. Visual Intelligence, 4(1). https://doi.org/10.1007/s44267-026-00107-3

Vancouver

Shan Y, Zhuge Y, Lu H. HDVS: semi-supervised semantic segmentation via heterogeneous dual-branch voting supervision. Visual Intelligence. 2026;4(1). doi:10.1007/s44267-026-00107-3

BibTeX
@article{Shan2026,
  author = {Shan, Yongqi and Zhuge, Yunzhi and Lu, Huchuan},
  title = {HDVS: semi-supervised semantic segmentation via heterogeneous dual-branch voting supervision},
  journal = {Visual Intelligence},
  year = {2026},
  volume = {4},
  number = {1},
  doi = {10.1007/s44267-026-00107-3}
}
Kostenlos starten →