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

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.

arXiv commentThis paper has been submitted to the journal for peer review. Based on the journal's policy and restrictions, this version may be updated or deleted

References in corpus (6)

• Remote Sensing Image Scene Classification: Benchmark and State of the Art
• AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification
• Multi-Granularity Canonical Appearance Pooling for Remote Sensing Scene Classification
• Enhanced Multi-level Features for Very High Resolution Remote Sensing Scene Classification
• Scene Image Representation by Foreground, Background and Hybrid Features
• Recent Advances in Scene Image Representation and Classification

Cited by in corpus (2)

• Enhanced Multi-level Features for Very High Resolution Remote Sensing Scene Classification
• Survey on Remote Sensing Scene Classification: From Traditional Methods to Large Generative AI Models