Skip to content
DraconiticResearch
Search Sources API
201,818 studies31 sourcesUpdated 59 min ago
Peer-reviewedCC BY 4.0PLOS One

ACMNet: An attention-convolution mixed neural network for semantic segmentation of high-resolution remote sensing images

  • Shangkun Yu1
  • Leijuan Yu2
  • Tingting Wang3
  • Rui Hu4
  • Chengxin Wang5
5 affiliations
  1. 1School of Geography and Tourism, Qilu Normal University, Jinan, China
  2. 2College of Geography and Environment, Shandong Normal University, Jinan, China
  3. 3School of Bioengineering, Shandong Polytechnic, Jinan, China
  4. 4Inspur Group Co., Ltd, Jinan, China
  5. 5Business School, University of Chinese Academy of Social Sciences, Beijing, China
Open at sourceDOICite

Abstract

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.

Related

  1. A parallel convolution attention network for crop genomic prediction
    Wenyu Peng, Yuxia Sheng, Ying Zhou
    PLOS OnePeer-reviewedCC BY 4.0Full textGenetics & genomicsStatisticsPLOS
  2. Agri-PIDNet-S: Lightweight semantic segmentation for field-structure and obstacle perception in seedling-stage cotton fields
    Yanlin Xin, Yongke Li, Wuchen Wei +3
    PLOS OnePeer-reviewedCC BYFull textPlant biologyPLOSEurope PMCPMC
  3. Attention warps visual-semantic representations across the human cerebellum
    A. LeBel, M. Visconti di Oleggio Castello, J. L. Gallant +1
    bioRxivPreprintCC BY-NC-NDFull textNeurosciencebioRxiv
  4. Individual Differences in Sustained Attention Tune Semantic Abstraction in Neural Encoding of Narratives
    S. Gao, Y. C. Leong, M. D. Rosenberg
    bioRxivPreprintCC BYFull textNeurosciencebioRxiv
  5. Harmonized Protocol for Segmentation of the Hippocampal Tail on High-Resolution In Vivo MRI From the Hippocampal Subfields Group (HSG).
    Robin de Flores, Kelsey L Canada, Thackery Brown +27
    HippocampusPeer-reviewedCC BY-NC-NDFull textNeuroscienceEurope PMC

Cite

BibTeXRIS
BibTeX
@article{yu2026acmnet,
  title = {{ACMNet: An attention-convolution mixed neural network for semantic segmentation of high-resolution remote sensing images}},
  author = {Shangkun Yu and Leijuan Yu and Tingting Wang and Rui Hu and Chengxin Wang},
  journal = {PLOS One},
  year = {2026},
  month = nov,
  doi = {10.1371/journal.pone.0358021},
  url = {https://doi.org/10.1371/journal.pone.0358021},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - ACMNet: An attention-convolution mixed neural network for semantic segmentation of high-resolution remote sensing images
AU  - Shangkun Yu
AU  - Leijuan Yu
AU  - Tingting Wang
AU  - Rui Hu
AU  - Chengxin Wang
PY  - 2026
DA  - 2026/11/06
JO  - PLOS One
DO  - 10.1371/journal.pone.0358021
UR  - https://doi.org/10.1371/journal.pone.0358021
AB  - 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.
SN  - 1932-6203
ER  -