Lightweight Attention Refined and Complex-Valued BiSeNetV2 for Semantic Segmentation of Polarimetric SAR Image

Highlights: What are the main findings? A novel lightweight attention-enhanced complex-valued BiSeNetV2 (LAM-CV-BiSeNetV2) is proposed for PolSAR image semantic segmentation. The designed Lightweight Attention Module (LAM) strengthens feature representation and alleviates the imbalance among polarization channels, achieving superior segmentation accuracy. What are the implications of the main findings? The proposed approach fully exploits complex-valued polarization information, outperforming existing segmentation networks on multiple datasets. This work provides a new lightweight and efficient attention module for high-precision PolSAR image understanding, contributing to the advancement of intelligent polarimetric remote sensing applications. In the semantic segmentation tasks of polarimetric SAR images, deep learning has become an important end-to-end method that uses convolutional neural networks (CNNs) and other advanced network architectures to extract features and classify the target region pixel by pixel. However, applying original networks used to optical images for PolSAR image segmentation directly will result in the loss of rich phase information in PolSAR data, which leads to unsatisfactory classification results. In order to make full use of polarization information, the complex-valued BiSeNetV2 with a bilateral-segmentation structure is studied and expanded in this work. Then, considering further improving the ability to extract semantic features in the complex domain and alleviating the imbalance of polarization channel response, the complex-valued BiSeNetV2 with a lightweight attention module (LAM-CV-BiSeNetV2) is proposed for the semantic segmentation of PolSAR images. LAM-CV-BiSeNetV2 supports complex-valued operations, and a lightweight attention module (LAM) is designed and introduced at the end of the Semantic Branch to enhance the extraction of detailed features. Compared with the original BiSeNetV2, the LAM-CV-BiSeNetV2 can not only more fully extract the phase information from polarimetric SAR data, but also has stronger semantic feature extraction capabilities. The experimental results on the Flevoland and San Francisco datasets demonstrate that the proposed LAM has better and more stable performance than other commonly used attention modules, and the proposed network can always obtain better classification results than BiSeNetV2 and other known real-valued networks.