MGML: Multi-Granularity Multi-Level Feature Ensemble Network for Remote Sensing Scene Classification

TL;DR

This paper introduces MGML-FENet, a novel network that combines multi-granularity and multi-level feature fusion with ensemble learning to improve remote sensing scene classification accuracy and interpretability.

Contribution

The paper presents a new multi-granularity multi-level feature ensemble network with specialized modules for extracting and combining diverse features, outperforming previous methods.

Findings

Achieves superior accuracy on multiple RS datasets.

Effectively handles intra-class variance and confusing information.

Provides interpretable visualization results.

Abstract

Remote sensing (RS) scene classification is a challenging task to predict scene categories of RS images. RS images have two main characters: large intra-class variance caused by large resolution variance and confusing information from large geographic covering area. To ease the negative influence from the above two characters. We propose a Multi-granularity Multi-Level Feature Ensemble Network (MGML-FENet) to efficiently tackle RS scene classification task in this paper. Specifically, we propose Multi-granularity Multi-Level Feature Fusion Branch (MGML-FFB) to extract multi-granularity features in different levels of network by channel-separate feature generator (CS-FG). To avoid the interference from confusing information, we propose Multi-granularity Multi-Level Feature Ensemble Module (MGML-FEM) which can provide diverse predictions by full-channel feature generator (FC-FG). Compared to previous methods, our proposed networks have ability to use structure information and abundant fine-grained features. Furthermore, through ensemble learning method, our proposed MGML-FENets can obtain more convincing final predictions. Extensive classification experiments on multiple RS datasets (AID, NWPU-RESISC45, UC-Merced and VGoogle) demonstrate that our proposed networks achieve better performance than previous state-of-the-art (SOTA) networks. The visualization analysis also shows the good interpretability of MGML-FENet.