.png){kind=icon}
返回
A segment anything model-based geological remote sensing interpretation method with a distributed data-parallel deep learning framework
.png){kind=icon}
OA
AI
DOI：10.1080/17538947.2025.2542913.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The interpretation of remote sensing images is pivotal in extracting geological elements of interest. Recent studies using deep learning models often fail to provide accurate boundaries between geological elements due to high interclass similarity and imbalanced data distribution. Furthermore, these models are computationally intensive. Inspired by expert interpretation practices, which involve first delineating boundaries and then identifying semantics, we leverage the vision foundation model and propose a distributed interpretation framework including distributed training and inference phases based on data parallelism in distributed architectures. First, a conventional semantic segmentation model, DeepLabV3, is trained. Subsequently, we integrate the Segment Anything Model (SAM) with the trained model, completing the final mapping during the inference phase. Specifically, the inference model features two branches: one for extracting masks by SAM and another for categorizing geological elements. Then, a semantic voting module combines the information from both branches to determine the category for each mask. Experiments demonstrate that the method enhanced the performance metric by more than 2%. Moreover, the method achieves a 3.85× speedup in training and a 3.95× speedup in inference on a 4-GPU machine. We further exploit simulation experiments of 16 GPUs and achieve up to 15.1× training speedup.
Keyword:
Geological remote sensing
semantic segmentation
SAM
distributed deep learning
期刊
IF:
4.9
论文数:
2.0K
被引数:
4.7K
机构
引用论文
Hajaj, S., A. El Harti, A. B. Pour, A. Jellouli, Z. Adiri, and M. Hashim. 2024. “A Review on Hyperspectral Imagery Application for Lithological Mapping and Mineral Prospecting: Machine Learning Techniques and Future Prospects.” Remote Sensing Applications: Society and Environment35:101218. https://doi.org/10.1016/j.rsase.2024.101218. (Open in a new window)Web of Science ®(Open in a new window)Google Scholar哈贾吉（Hajaj），S.，艾尔·哈蒂（El Harti），A.，波尔（Pour），A. B.，杰洛利（Jellouli），A.，阿德里（Adiri），Z.，哈希姆（Hashim），M.。2024年。“高光谱成像技术在岩石地层制图和矿产勘探中的应用综述：机器学习技术与未来展望。”《遥感应用：社会与环境》，第35卷，第101218页。https://doi.org/10.1016/j.rsase.2024.101218。（在新窗口中打开）Web of Science ®（在新窗口中打开）谷歌学术。.png)
IF0
PREAI
分享收藏Wang, S., X. Huang, W. Han, X. Zhang, and J. Li. 2024. “Geological Remote Sensing Interpretation via a Local-to-Global Sensitive Feature Fusion Network.” International Journal of Applied Earth Observation and Geoinformation 135:104258. https://doi.org/10.1016/j.jag.2024.104258. (Open in a new window)Web of Science ®(Open in a new window)Google Scholar王, S., 黄 X., 韩 W., 张 X., 李 J. 2024. “基于局部到全局敏感特征融合网络的地质遥感解译.” 国际地球观测与应用地理信息杂志 135:104258. https://doi.org/10.1016/j.jag.2024.104258. (在新窗口中打开)Web of Science ®(在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏Han, W., L. Wang, Y. Wang, J. Li, J. Yan, and Y. Shao. 2025. “A Novel Framework for Leveraging Geological Environment Big Data to Assess Sustainable Development Goals.” The Innovation Geoscience 3:100122. https://doi.org/10.59717/j.xinn-geo.2024.100122. (Open in a new window)Google ScholarHan, W., L. Wang, Y. Wang, J. Li, J. Yan, and Y. Shao. 2025. “利用地质环境大数据评估可持续发展目标的新框架。” 《创新地球科学》3:100122. https://doi.org/10.59717/j.xinn-geo.2024.100122. (在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏Li, X., F. Xu, F. Liu, X. Lyu, Y. Tong, Z. Xu, and J. Zhou. 2023. “A Synergistical Attention Model for Semantic Segmentation of Remote Sensing Images.” IEEE Transactions on Geoscience and Remote Sensing 61:1–16. (Open in a new window)Web of Science ®(Open in a new window)Google ScholarLi, X., F. Xu, F. Liu, X. Lyu, Y. Tong, Z. Xu, and J. Zhou. 2023. “一种用于遥感图像语义分割的协同注意模型。” IEEE 地球科学与遥感汇刊 61:1–16. (在新窗口中打开)Web of Science ®(在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏Li, X., F. Xu, A. Yu, X. Lyu, H. Gao, and J. Zhou. 2025. “A Frequency Decoupling Network for Semantic Segmentation of Remote Sensing Images.” IEEE Transactions on Geoscience and Remote Sensing 63:1–21. (Open in a new window)Web of Science ®(Open in a new window)Google ScholarLi, X., F. Xu, A. Yu, X. Lyu, H. Gao, and J. Zhou. 2025. “一种用于遥感图像语义分割的频率解耦网络。” IEEE 地球科学与遥感汇刊 63:1–21. (在新窗口中打开)Web of Science ®(在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏Han, W., X. Zhang, Y. Wang, L. Wang, X. Huang, J. Li, S. Wang, et al. 2023. “A Survey of Machine Learning and Deep Learning in Remote Sensing of Geological Environment: Challenges, Advances, and Opportunities.” ISPRS Journal of Photogrammetry and Remote Sensing 202:87–113. https://doi.org/10.1016/j.isprsjprs.2023.05.032. (Open in a new window)Web of Science ®(Open in a new window)Google ScholarHan, W., Zhang, X., Wang, Y., Wang, L., Huang, X., Li, J., Wang, S., et al. 2023. “遥感地质环境中的机器学习与深度学习综述：挑战、进展与机遇。” 《摄影测量与遥感学报》202:87–113. https://doi.org/10.1016/j.isprsjprs.2023.05.032. (在新窗口中打开) Web of Science ®(在新窗口中打开) Google Scholar
IF0
PREAI
分享收藏Wang, M., Z. Huang, X. Zhang, Y. Zhang, and M. Chen. 2021. “Altered Mineral Mapping Based on Ground-Airborne Hyperspectral Data and Wavelet Spectral Angle Mapper Tri-training Model: Case Studies from Dehua-Youxi-Yongtai Ore District, Central Fujian, China.” International Journal of Applied Earth Observation and Geoinformation 102:102409. https://doi.org/10.1016/j.jag.2021.102409. (Open in a new window)Web of Science ®(Open in a new window)Google Scholar王，M.，黄，Z.，张，X.，张，Y.，陈，M.。2021年。“基于地面-机载高光谱数据和连续小波谱角映射三训练模型的矿物制图方法：以中国福建省中部德化-尤溪-永泰矿区的案例研究为例。”《国际地球观测与应用地理信息杂志》102卷：102409。https://doi.org/10.1016/j.jag.2021.102409。（在新窗口中打开）Web of Science ®（在新窗口中打开）Google Scholar
IF0
PREAI
分享收藏Kirillov, Alexander, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, et al. 2023. “Segment Anything.” arXiv Preprint arXiv:2304.02643. (Open in a new window)Google ScholarKirillov, Alexander, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, et al. 2023. “分割一切。” arXiv预印本 arXiv:2304.02643. (在新窗口中打开)谷歌学术
IF0
PREAI
分享收藏Haut, J. M., J. A. G. Jaramago, M. E. Paoletti, G. Cavallaro, J. Plaza, A. Plaza, and M. Riedel. 2019. “Cloud Deep Networks for Hyperspectral Image Analysis.” IEEE Transactions on Geoscience and Remote Sensing 57 (12): 9832–9848. https://doi.org/10.1109/TGRS.36. (Open in a new window)Web of Science ®(Open in a new window)Google ScholarHaut, J. M., J. A. G. Jaramago, M. E. Paoletti, G. Cavallaro, J. Plaza, A. Plaza, and M. Riedel. 2019. “云深度网络用于高光谱图像分析。” IEEE 地球科学与遥感汇刊 57 (12): 9832–9848. https://doi.org/10.1109/TGRS.36. (在新窗口中打开)Web of Science ®(在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏Liu, H., K. Wu, H. Xu, and Y. Xu. 2021. “Lithology Classification Using TASI Thermal Infrared Hyperspectral Data with Convolutional Neural Networks.” Remote Sensing 13 (16): 3117. https://doi.org/10.3390/rs13163117. (Open in a new window)Web of Science ®(Open in a new window)Google Scholar刘, H., 吴, K., 徐, H., 和徐, Y. 2021. “利用卷积神经网络和TASI热红外高光谱数据进行岩性分类。” 遥感 13 (16): 3117. https://doi.org/10.3390/rs13163117. (在新窗口中打开)Web of Science ®(在新窗口中打开)Google Scholar
IF0
PREAI
分享收藏
查看更多内容