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

arXiv: https://arxiv.org/abs/2210.17419 · HTML: https://mlsanity.com/paper/2210.17419/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 58 references that are in the map.
- First posted on arXiv 28 Oct 2022.

## Builds on (most cited first, 9 of 9)

- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Deep Complex Networks](https://mlsanity.com/paper/1705.09792/) (2017)
- [A Survey of Complex-Valued Neural Networks](https://mlsanity.com/paper/2101.12249/) (2021)
- [Complex-valued Neural Networks with Non-parametric Activation Functions](https://mlsanity.com/paper/1802.08026/) (2018)
- [Complex-Valued vs. Real-Valued Neural Networks for Classification Perspectives: An Example on Non-Circular Data](https://mlsanity.com/paper/2009.08340/) (2020)
- [Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional Network](https://mlsanity.com/paper/1909.13299/) (2019)
- [Automatic Design of CNNs via Differentiable Neural Architecture Search for PolSAR Image Classification](https://mlsanity.com/paper/1911.06993/) (2019)
- [Semi-supervised Complex-valued GAN for Polarimetric SAR Image Classification](https://mlsanity.com/paper/1906.03605/) (2019)
- [CoShNet: A Hybrid Complex Valued Neural Network using Shearlets](https://mlsanity.com/paper/2208.06882/) (2022)

## Built on by (most cited first, 1 of 1)

- [DeepCSHAP: Utilizing Shapley Values to Explain Deep Complex-Valued Neural Networks](https://mlsanity.com/paper/2403.08428/) (2024)

## Abstract (arXiv)

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.