Enhanced Multi-level Features for Very High Resolution Remote Sensing Scene Classification

TL;DR

This paper introduces a novel deep learning approach with an enhanced attention module and multi-level feature fusion to improve the stability and accuracy of very high-resolution remote sensing scene classification.

Contribution

It proposes an enhanced VHR attention module combined with ASPP and GAP for more robust feature extraction and fusion in VHR RS scene classification.

Findings

Achieved highest accuracy of 95.39% on AID dataset

Achieved highest accuracy of 93.04% on NWPU dataset

Demonstrated stable classification with minimal standard deviation

Abstract

Very high-resolution (VHR) remote sensing (RS) scene classification is a challenging task due to the higher inter-class similarity and intra-class variability problems. Recently, the existing deep learning (DL)-based methods have shown great promise in VHR RS scene classification. However, they still provide an unstable classification performance. To address such a problem, we, in this letter, propose a novel DL-based approach. For this, we devise an enhanced VHR attention module (EAM), followed by the atrous spatial pyramid pooling (ASPP) and global average pooling (GAP). This procedure imparts the enhanced features from the corresponding level. Then, the multi-level feature fusion is performed. Experimental results on two widely-used VHR RS datasets show that the proposed approach yields a competitive and stable/robust classification performance with the least standard deviation of 0.001. Further, the highest overall accuracies on the AID and the NWPU datasets are 95.39% and 93.04%, respectively.