DDF2Pol: A Dual-Domain Feature Fusion Network for PolSAR Image Classification

TL;DR

DDF2Pol is a lightweight dual-domain CNN that effectively classifies PolSAR images by combining real and complex features, achieving high accuracy with low complexity.

Contribution

It introduces a novel dual-domain architecture with attention mechanisms, outperforming existing models in PolSAR classification tasks.

Findings

Achieves 98.16% accuracy on Flevoland dataset.

Attains 96.12% accuracy on San Francisco dataset.

Uses only 91,371 parameters, demonstrating efficiency.

Abstract

This paper presents DDF2Pol, a lightweight dual-domain convolutional neural network for PolSAR image classification. The proposed architecture integrates two parallel feature extraction streams, one real-valued and one complex-valued, designed to capture complementary spatial and polarimetric information from PolSAR data. To further refine the extracted features, a depth-wise convolution layer is employed for spatial enhancement, followed by a coordinate attention mechanism to focus on the most informative regions. Experimental evaluations conducted on two benchmark datasets, Flevoland and San Francisco, demonstrate that DDF2Pol achieves superior classification performance while maintaining low model complexity. Specifically, it attains an Overall Accuracy (OA) of 98.16% on the Flevoland dataset and 96.12% on the San Francisco dataset, outperforming several state-of-the-art real- and complex-valued models. With only 91,371 parameters, DDF2Pol offers a practical and efficient solution for accurate PolSAR image analysis, even when training data is limited. The source code is publicly available at https://github.com/mqalkhatib/DDF2Pol