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

Abstract 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...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Yongqi Shan, Yunzhi Zhuge, Huchuan Lu
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Springer 2026-02-01
Edice:	Visual Intelligence
Témata:	Semi-supervised semantic segmentation Feature communication Voting mechanism Heterogeneous dual-branch networks
On-line přístup:	https://doi.org/10.1007/s44267-026-00107-3
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!