Unsupervised Land-Cover Segmentation Using Accelerated Balanced Deep Embedded Clustering

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.

Automated summary

This letter introduces a novel deep learning clustering algorithm for automatic labeling of remote sensing datasets, which addresses the issue of data imbalance in the deep embedded clustering (DEC) algorithm through additional search and extraction steps. The proposed algorithm is highly parallelizable and achieves significant performance speedup (40X to 2600X) and improved clustering accuracy compared to DEC and other clustering approaches.