Towards Spatial Variability Aware Deep Neural Networks (SVANN): A Summary of Results

Towards Spatial Variability Aware Deep Neural Networks (SVANN): A Summary of Results
复制标题

迈向空间变异感知深度神经网络 (SVANN):结果摘要

DOI:
--
复制
发表时间:
2020
期刊:
arXiv.org
影响因子:
--
通讯作者:
S. Shekhar
S. Shekhar
中科院分区:
--
文献类型:
--
作者:
Jayant Gupta;Yiqun Xie;S. Shekhar

文献摘要

参考文献

被引文献

相似文献

在许多地理现象中观察到了空间变异性,包括气候带、USDA植物耐寒带和陆地栖息地类型(例如,森林、草原、湿地和沙漠)。然而,目前的深度学习方法遵循空间一刀切(OSFA)方法来训练不考虑空间变异性的单个深度神经网络模型。在这项工作中,我们提出并研究了一种空间可变性感知深度神经网络(SVANN)方法,其中为每个地理区域构建了不同的深度神经网络模型。我们评估这种方法使用航空影像从两个地理区域的任务,绘制城市花园。实验结果表明,SVANN提供了更好的性能比OSFA的精度,召回率和F1得分,以识别城市花园。
Spatial variability has been observed in many geo-phenomena including climatic zones, USDA plant hardiness zones, and terrestrial habitat types (e.g., forest, grasslands, wetlands, and deserts). However, current deep learning methods follow a spatial-one-size-fits-all(OSFA) approach to train single deep neural network models that do not account for spatial variability. In this work, we propose and investigate a spatial-variability aware deep neural network(SVANN) approach, where distinct deep neural network models are built for each geographic area. We evaluate this approach using aerial imagery from two geographic areas for the task of mapping urban gardens. The experimental results show that SVANN provides better performance than OSFA in terms of precision, recall,and F1-score to identify urban gardens.
DOI: 10.1148/rg.2017160130
发表时间: 2017-03
期刊: Radiographics : a review publication of the Radiological Society of North America, Inc
影响因子: --
作者:
Erickson BJ;Korfiatis P;Akkus Z;Kline TL
通讯作者: Kline TL
DOI: 10.1109/icdm.2018.00183
发表时间: 2018-11
期刊: 2018 IEEE International Conference on Data Mining (ICDM)
影响因子: --
作者:
Yiqun Xie;Han Bao;S. Shekhar;Joseph K. Knight
通讯作者: Yiqun Xie;Han Bao;S. Shekhar;Joseph K. Knight
DOI: 10.1109/isc2.2018.8656800
发表时间: 2018-09
期刊: 2018 IEEE International Smart Cities Conference (ISC2)
影响因子: --
作者:
Yiqun Xie;Jayant Gupta;Yan Li;S. Shekhar
通讯作者: Yiqun Xie;Jayant Gupta;Yan Li;S. Shekhar
通过智能空间技术彻底改变树木管理
DOI: 10.1145/3347146.3359066
发表时间: 2019
期刊: SIGSPATIAL '19: Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems
影响因子: --
作者:
Xie, Yiqun;Shekhar, Shashi;Feiock, Richard;Knight, Joseph
通讯作者: Knight, Joseph
DOI: 10.1145/3337798
发表时间: 2019-08-01
影响因子: 5
作者:
Jiang, Zhe;Sainju, Arpan Man;Knight, Joseph
通讯作者: Knight, Joseph