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

Lei Ding, Kai Zheng, Dong Lin, Yuxing Chen, Bing Liu, Jiansheng Li, Lorenzo Bruzzone

Introduction

Semantic segmentation of Polarimetric SAR (PolSAR) images is notoriously difficult due to intense speckle noise and a historical lack of large training datasets. This paper introduces MP-ResNet, a Multi-path Residual Network designed to capture broader contextual information and mitigate noise through parallel multi-scale branches. By effectively enlarging the network's receptive field without a massive computational penalty, MP-ResNet achieves state-of-the-art performance on high-resolution Gaofen benchmarks.

The Challenge of PolSAR Segmentation

Synthetic Aperture Radar (SAR) is invaluable for Earth observation due to its all-weather, day-and-night imaging capabilities. However, segmenting high-resolution PolSAR images into land-cover classes faces two major hurdles:

  1. Speckle Noise: The coherent imaging mechanism of SAR systems creates intense, granular noise, making pixel-level signals highly erratic.
  2. Data Scarcity: Deep learning models require massive amounts of labeled data, which has historically been scarce for SAR. This often leads researchers to use shallow networks that fail to capture the high-level semantic context needed to look past noise.

Methodology: The MP-ResNet Architecture

The authors propose the Multi-path Residual Network (MP-ResNet), which builds upon a Fully Convolutional Network (FCN) with a ResNet backbone.

The MP-ResNet architecture features parallel encoding branches to capture multi-scale context.

Key innovations include:

  • Quick Embedding of Shallow Features: A large 7x7 initial convolutional kernel aggregates features from a wider neighborhood to smooth speckle noise early. The feature scale is quickly reduced to 1/8, identified as the "sweet spot" for regional modeling.
  • Multi-path Semantic Embedding: Inspired by HRNet, MP-ResNet splits into three parallel encoding branches. Unlike HRNet, it focuses purely on high-level features to enlarge the Valid Receptive Field (VRF), allowing the network to use broad spatial context to identify noisy pixels.
  • Coarse-to-Fine Decoder Fusion: Instead of standard skip connections that might reintroduce low-level noise, MP-ResNet uses a channel-wise "Bottleneck" spatial deconvolution module to fuse only rich, high-level semantic features from its parallel encoder branches.

Experimental Results

MP-ResNet was evaluated on the Gaofen dataset (Gaofen-3 satellite, 1m-3m resolution). The model achieved an Overall Accuracy (OA) of 93.95% and a mean F1 score of 92.47% on validation sets.

Comparison of MP-ResNet against state-of-the-art segmentation methods.

As shown in the comparison table, MP-ResNet outperforms standard optical segmentation models like DeepLabV3+ and PSPNet, as well as SAR-specific models like MS-FCN. Notably, it achieved a 1.23% fwIoU boost on the hidden contest test set, securing 2nd place in the Gaofen Challenge.

In terms of efficiency, MP-ResNet requires 115.93 GFLOPS. While slightly higher than the baseline FCN (90.97 GFLOPS), it remains significantly more efficient than architectures like UNet (221.68 GFLOPS) or SegNet (341.06 GFLOPS).

Conclusion

MP-ResNet demonstrates that context is the ultimate noise filter for PolSAR imagery. By prioritizing broad spatial context over local pixel intensities and avoiding noise-prone low-level skip connections, the architecture sets a new benchmark for high-resolution SAR land-cover classification. Future work will explore integrating attention mechanisms and dilated convolutions to further refine performance.

Summary updated

BibTeX
@article{ding2022mp,
  author = {Lei Ding and Kai Zheng and Dong Lin and Yuxing Chen and Bing Liu and Jiansheng Li and Lorenzo Bruzzone},
  title = {{MP-ResNet: Multi-path Residual Network for the Semantic segmentation of High-Resolution PolSAR Images}},
  journal = {IEEE Geosci. Remote. Sens. Lett.},
  year = {2022},
  doi = {10.1109/lgrs.2021.3079925},
}
Figure