A Complex-Valued PolSAR Image Segmentation Network With Lovász-Softmax Loss Optimization

In recent years, complex-valued convolutional neural networks have emerged as a promising approach for PolSAR image segmentation by utilizing both amplitude and phase information in PolSAR data. This paper introduces a complex-valued network for PolSAR image segmentation termed as CV-LoSARNet, which is in fact a complex-valued Lovász-softmax loss optimization framework. The bilateral structure of CV-LoSARNet provides efficient feature extraction, while the complex-valued network adapting to PolSAR data can improve feature extraction capabilities. The introduced loss function combines both the Lovász-softmax loss and cross-entropy loss, which can improve the optimization objective of the segmentation. Comparative experiments conducted on E-SAR data and AIRSAR data demonstrate the superiority of the proposed network over the classical full convolutional neural network and the classic bilateral networks. Compared with the classic bilateral network, the CV-LoSARNet has improved the MIOU and MPA of E-SAR data sets by 2.37% and 2.29%, for AIRSAR data sets the improvement is 12.95% and 6.70%. Moreover, the segmentation performance of the proposed network on different polarimetric modes is discussed.