MP-ResNet: Multi-path Residual Network for the Semantic segmentation of High-Resolution PolSAR Images

TL;DR

This paper introduces MP-ResNet, a multi-path residual network architecture designed for improved semantic segmentation of high-resolution PolSAR images, leveraging multi-scale features and multi-level fusion.

Contribution

The paper proposes a novel multi-path ResNet architecture with multi-scale branches and feature fusion, outperforming existing methods on PolSAR image segmentation.

Findings

MP-ResNet achieves higher accuracy than baseline models.

It surpasses state-of-the-art methods in OA, F1, and fwIoU.

The architecture maintains low computational costs.

Abstract

There are limited studies on the semantic segmentation of high-resolution Polarimetric Synthetic Aperture Radar (PolSAR) images due to the scarcity of training data and the inference of speckle noises. The Gaofen contest has provided open access of a high-quality PolSAR semantic segmentation dataset. Taking this chance, we propose a Multi-path ResNet (MP-ResNet) architecture for the semantic segmentation of high-resolution PolSAR images. Compared to conventional U-shape encoder-decoder convolutional neural network (CNN) architectures, the MP-ResNet learns semantic context with its parallel multi-scale branches, which greatly enlarges its valid receptive fields and improves the embedding of local discriminative features. In addition, MP-ResNet adopts a multi-level feature fusion design in its decoder to make the best use of the features learned from its different branches. Ablation studies show that the MPResNet has significant advantages over its baseline method (FCN with ResNet34). It also surpasses several classic state-of-the-art methods in terms of overall accuracy (OA), mean F1 and fwIoU, whereas its computational costs are not much increased. This CNN architecture can be used as a baseline method for future studies on the semantic segmentation of PolSAR images. The code is available at: https://github.com/ggsDing/SARSeg.