Semi-Supervised Semantic Segmentation via Derivative Label Propagation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 4058-4066
DOI: 10.1609/aaai.v40i5.37409 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yuanbin Fu und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Semi-supervised semantic segmentation, which leverages a limited set of labeled images, helps to relieve the heavy annotation burden. While pseudo-labeling strategies yield promising results, there is still room for enhancing the reliability of pseudo-labels. Hence, we develop a semi-supervised framework, namely DerProp, equipped with a novel derivative label propagation to rectify imperfect pseudo-labels. Our label propagation method imposes discrete derivative operations on pixel-wise feature vectors as additional regularization, thereby generating strictly regularized similarity metrics. Doing so effectively alleviates the ill-posed problem that identical similarities correspond to different features, through constraining the solution space. Extensive experiments are conducted to verify the rationality of our design, and demonstrate our superiority over other methods.
Zitieren
APA
Fu, Y., & Guo, X. (2026). Semi-Supervised Semantic Segmentation via Derivative Label Propagation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 4058-4066. https://doi.org/10.1609/aaai.v40i5.37409
Vancouver
Fu Y, Guo X. Semi-Supervised Semantic Segmentation via Derivative Label Propagation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):4058-4066. doi:10.1609/aaai.v40i5.37409
BibTeX
@article{Fu2026,
author = {Fu, Yuanbin and Guo, Xiaojie},
title = {Semi-Supervised Semantic Segmentation via Derivative Label Propagation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {5},
pages = {4058--4066},
doi = {10.1609/aaai.v40i5.37409}
}
EUVIMED