Impact of PolSAR pre-processing and balancing methods on complex-valued neural networks segmentation tasks

TL;DR

This paper evaluates how different pre-processing and balancing techniques affect the performance of complex-valued neural networks in PolSAR image segmentation, highlighting the importance of data handling and class imbalance.

Contribution

It provides a comprehensive comparison of input representations, model architectures, and pre-processing methods, introducing new techniques to mitigate dataset bias and class imbalance in PolSAR segmentation.

Findings

Pauli vector is a valid alternative to coherency matrix as input.

Data splitting can cause high correlation, inflating performance metrics.

Proposed balancing methods improve class-wise segmentation performance.

Abstract

In this paper, we investigated the semantic segmentation of Polarimetric Synthetic Aperture Radar (PolSAR) using Complex-Valued Neural Network (CVNN). Although the coherency matrix is more widely used as the input of CVNN, the Pauli vector has recently been shown to be a valid alternative. We exhaustively compare both methods for six model architectures, three complex-valued, and their respective real-equivalent models. We are comparing, therefore, not only the input representation impact but also the complex- against the real-valued models. We then argue that the dataset splitting produces a high correlation between training and validation sets, saturating the task and thus achieving very high performance. We, therefore, use a different data pre-processing technique designed to reduce this effect and reproduce the results with the same configurations as before (input representation and model architectures). After seeing that the performance per class is highly different according to class occurrences, we propose two methods for reducing this gap and performing the results for all input representations, models, and dataset pre-processing.