Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces DDF2Pol, a dual-stream CNN architecture for Polarimetric Synthetic Aperture Radar (PolSAR) image classification that processes real and complex-valued data in parallel to extract spatial and polarimetric features. The network incorporates depth-wise convolutions for spatial enhancement and coordinate attention to focus on informative regions. Experiments on Flevoland and San Francisco datasets demonstrate that DDF2Pol achieves state-of-the-art classification accuracy (98.16% and 96.12% OA, respectively) with a lightweight architecture of only 91,371 parameters.
You can achieve state-of-the-art PolSAR image classification with a CNN that has less than 100k parameters by fusing real and complex-valued feature extraction streams.
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