U-NetMN and SegNetMN: Modified U-Net and SegNet models for bimodal SAR image segmentation

TL;DR

This paper introduces mode normalization into U-Net and SegNet models for SAR image segmentation, significantly improving convergence speed and stability without sacrificing performance.

Contribution

The study demonstrates that integrating mode normalization into existing models enhances convergence speed and stability in SAR image segmentation tasks.

Findings

Mode normalization accelerates model convergence.

Normalized models show increased stability across zones.

Performance remains comparable to baseline models.

Abstract

Segmenting Synthetic Aperture Radar (SAR) images is crucial for many remote sensing applications, particularly water body detection. However, deep learning-based segmentation models often face challenges related to convergence speed and stability, mainly due to the complex statistical distribution of this type of data. In this study, we evaluate the impact of mode normalization on two widely used semantic segmentation models, U-Net and SegNet. Specifically, we integrate mode normalization, to reduce convergence time while maintaining the performance of the baseline models. Experimental results demonstrate that mode normalization significantly accelerates convergence. Furthermore, cross-validation results indicate that normalized models exhibit increased stability in different zones. These findings highlight the effectiveness of normalization in improving computational efficiency and generalization in SAR image segmentation.