POLSAR IMAGE CLASSIFICATION VIA FEATURE SELECTION AND EDGE PRESERVATION USING ATTENTION-BASED CNN

Observing that the integration of polarimetric features with physical attributes in Polarimetric Synthetic Aperture Radar (PolSAR) images yields superior decoupling compared to individual statistical features. In response to the challenge, the Attention-based Feature Selection and Edge Preservation CNN (AFE-CNN) is proposed, which integrates a channel attention mechanism to dynamically assign weights to input features and employs a multi-scale spatial attention mechanism to prioritize edge information. Specifically addressing edge confusion in Polarimetric Synthetic Aperture Radar (PolSAR) image classification, this approach ensures the preservation of crucial edge details through judicious selection and utilization of input features. The effectiveness of AFE-CNN is validated through end-to-end classification of PolSAR images on two widely utilized datasets.