An Attention-Fused Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Imagery

TL;DR

This paper introduces AFNet, a novel neural network architecture that effectively fuses multi-source and multi-level features for improved semantic segmentation of very-high-resolution remote sensing images, achieving state-of-the-art accuracy.

Contribution

The paper proposes a new attention-fused network with multipath feature extraction and fusion modules tailored for remote sensing imagery segmentation.

Findings

Achieved 91.7% overall accuracy on ISPRS Vaihingen dataset.

Achieved 92.1% overall accuracy on ISPRS Potsdam dataset.

Outperformed existing methods in semantic segmentation accuracy.

Abstract

Semantic segmentation is an essential part of deep learning. In recent years, with the development of remote sensing big data, semantic segmentation has been increasingly used in remote sensing. Deep convolutional neural networks (DCNNs) face the challenge of feature fusion: very-high-resolution remote sensing image multisource data fusion can increase the network's learnable information, which is conducive to correctly classifying target objects by DCNNs; simultaneously, the fusion of high-level abstract features and low-level spatial features can improve the classification accuracy at the border between target objects. In this paper, we propose a multipath encoder structure to extract features of multipath inputs, a multipath attention-fused block module to fuse multipath features, and a refinement attention-fused block module to fuse high-level abstract features and low-level spatial features. Furthermore, we propose a novel convolutional neural network architecture, named attention-fused network (AFNet). Based on our AFNet, we achieve state-of-the-art performance with an overall accuracy of 91.7% and a mean F1 score of 90.96% on the ISPRS Vaihingen 2D dataset and an overall accuracy of 92.1% and a mean F1 score of 93.44% on the ISPRS Potsdam 2D dataset.