ACMNet: An attention-convolution mixed neural network for semantic segmentation of high-resolution remote sensing images
PLOS One · 06.11.2026 · 21 (11) · e0358021
DOI: 10.1371/journal.pone.0358021 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 06.11.2026. Verfasst von Shangkun Yu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Geography and Tourism, Qilu Normal University, Jinan, China. Hauptthemen laut MEDLINE: Remote Sensing Technology, Image Processing, Computer-Assisted, Neural Networks, Computer. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Major Project of Key Research Bases for Humanities and Social Sciences Funded by the Ministry of Education of China, Jinan Municipal Philosophy and Social Sciences Planning Research Project.
Abstract (Originalsprache)
Semantic segmentation of remote sensing imagery, which is widely used in land cover classification, urban planning, and environmental monitoring, has become a research hotspot in the fields of remote sensing and computer vision. As its applications continue to expand, improving the segmentation accuracy and generalization have become pressing challenges. However, most existing semantic segmentation models rely solely on either attention mechanisms or convolutional neural networks (CNNs), thus leaving room for performance improvement. In this study, we propose ACMNet (Attention-Convolution Mixed Network), which adopts a hybrid attention-convolution architecture. The decoder of ACMNet employs an innovative mixed design, where two branches are used to extract and integrate different types of contextual information and achieve hierarchical aggregation of contextual features, thereby enhancing its performance. To evaluate the performance of ACMNet, we conducted ablation experiments and comparative experiments on the Potsdam, Vaihingen, and WHU Building datasets. The results show that ACMNet achieved the best overall performance across all three datasets, with mF1 scores of 91.79%, 88.70%, and 96.56% on the Potsdam, Vaihingen, and WHU Building datasets, respectively. These findings indicate that ACMNet delivers superior performance in the semantic segmentation of high-resolution remote sensing images in urban areas, which provides valuable support for diverse tasks related to fine-grained urban management and dynamic monitoring.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Geography and Tourism, Qilu Normal University, Jinan, China.
- College of Geography and Environment, Shandong Normal University, Jinan, China.
- School of Bioengineering, Shandong Polytechnic, Jinan, China.
- Inspur Group Co., Ltd, Jinan, China.
- Business School, University of Chinese Academy of Social Sciences, Beijing, China.
- Key Research Institute of Yellow River Civilization and Sustainable Development & Yellow River Civilization by Provincial and Ministerial Co-construction of Collaborative Innovation Center, Henan University, Kaifeng, Ch…
ORCID-Profile: Shangkun Yu
Förderung
- Major Project of Key Research Bases for Humanities and Social Sciences Funded by the Ministry of Education of China
- Jinan Municipal Philosophy and Social Sciences Planning Research Project
Zitieren
APA
Yu, S., Yu, L., Wang, T., Hu, R., & Wang, C. (2026). ACMNet: An attention-convolution mixed neural network for semantic segmentation of high-resolution remote sensing images. PLOS One, 21(11), e0358021. https://doi.org/10.1371/journal.pone.0358021
Vancouver
Yu S, Yu L, Wang T, Hu R, Wang C. ACMNet: An attention-convolution mixed neural network for semantic segmentation of high-resolution remote sensing images. PLOS One. 2026;21(11):e0358021. doi:10.1371/journal.pone.0358021
BibTeX
@article{Yu2026,
author = {Yu, Shangkun and Yu, Leijuan and Wang, Tingting and Hu, Rui and Wang, Chengxin},
title = {ACMNet: An attention-convolution mixed neural network for semantic segmentation of high-resolution remote sensing images},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {11},
pages = {e0358021},
doi = {10.1371/journal.pone.0358021}
}
EUVIMED