MCDiff: A Multilevel Conditional Diffusion Model for PolSAR Image Classification

Abstract

With the swift advancement of deep learning, significant strides have been made in polarimetric synthetic aperture radar (PolSAR) image classification, particularly with the advent of diffusion models that allow for explicit class probability modeling. However, existing diffusion models have yet to fully leverage the rich polarimetric characteristics of PolSAR images. To address this, we propose the multilevel conditional diffusion (MCDiff) model for PolSAR image classification, incorporating three key strategies. First, a prior learning module is constructed to capture scattering characteristics across all three polarization basis parameter spaces, providing conditional guidance for the diffusion model. Second, a multiscale and multidimensional noise prediction module is designed to reduce the information loss when noisy labels and image features of different dimensions are fused to predict noise. Finally, a multilevel high-order statistical feature learning module is introduced to aid in the additive Gaussian noise prediction of noisy labels while mitigating the impact of PolSAR images' multiplicative speckle noise on the prediction. Experimental results on three benchmark datasets confirm MCDiff's ability to achieve high-performance explicit class probability modeling for PolSAR images among the compared methods.