Unsupervised Land-Cover Segmentation Using Accelerated Balanced Deep Embedded Clustering

Unsupervised Land-Cover Segmentation Using Accelerated Balanced Deep Embedded Clustering
复制标题

使用加速平衡深度嵌入聚类的无监督土地覆盖分割

DOI:
--
复制
发表时间:
2022
影响因子:
4.8
通讯作者:
N. Werghi
N. Werghi
中科院分区:
工程技术2区
文献类型:
--
作者:
Ahmad Obeid;I. Elfadel;N. Werghi

文献摘要

被引文献

相似文献

在这封信中,我们使用一种新的深度学习聚类算法来解决遥感数据集的自动标记问题。该算法解决了固有的敏感性的深度嵌入式聚类(DEC)算法的数据不平衡,使用额外的搜索和提取步骤。此外,该算法是高度并行化。一个图形处理单元(GPU)的实现,以实现40倍到2600倍的性能加速和改进的聚类精度相对于DEC和其他聚类方法。
In this letter, we address the issue of the automatic labeling of remote sensing datasets using a novel deep learning clustering algorithm. The proposed algorithm addresses the inherent susceptibility of the deep embedded clustering (DEC) algorithm to data imbalance using additional search and extraction steps. Furthermore, the proposed algorithm is highly parallelizable. A graphics processing unit (GPU) implementation is shown to achieve 40X to 2600X of performance speedup and improved clustering accuracy with respect to DEC and other clustering approaches.