A Multi-Stage Duplex Fusion ConvNet for Aerial Scene Classification

TL;DR

This paper introduces a lightweight multi-stage duplex fusion ConvNet (MSDF-Net) for aerial scene classification that achieves high accuracy with significantly fewer parameters, suitable for real-time remote sensing applications.

Contribution

The paper proposes a novel residual-dense duplex fusion strategy and duplex semantic aggregation module to enhance feature propagation while reducing model complexity.

Findings

Achieves 92.96% accuracy on AID dataset.

Reduces parameters by up to 80% compared to state-of-the-art.

Demonstrates competitive performance on three benchmarks.

Abstract

Existing deep learning based methods effectively prompt the performance of aerial scene classification. However, due to the large amount of parameters and computational cost, it is rather difficult to apply these methods to multiple real-time remote sensing applications such as on-board data preception on drones and satellites. In this paper, we address this task by developing a light-weight ConvNet named multi-stage duplex fusion network (MSDF-Net). The key idea is to use parameters as little as possible while obtaining as strong as possible scene representation capability. To this end, a residual-dense duplex fusion strategy is developed to enhance the feature propagation while re-using parameters as much as possible, and is realized by our duplex fusion block (DFblock). Specifically, our MSDF-Net consists of multi-stage structures with DFblock. Moreover, duplex semantic aggregation (DSA) module is developed to mine the remote sensing scene information from extracted convolutional features, which also contains two parallel branches for semantic description. Extensive experiments are conducted on three widely-used aerial scene classification benchmarks, and reflect that our MSDF-Net can achieve a competitive performance against the recent state-of-art while reducing up to 80% parameter numbers. Particularly, an accuracy of 92.96% is achieved on AID with only 0.49M parameters.