Knowledge-guided Complex Diffusion Model for PolSAR Image Classification in Contourlet Domain

2025-07-08

AI Summary

Traditional real-valued diffusion models struggle to capture complex-phase information and preserve edge details in Polarimetric Synthetic Aperture Radar (PolSAR) image classification. To address this, we propose a Contourlet-domain structural-knowledge-guided complex diffusion model. Our approach is the first to embed a complex-valued diffusion process within the multi-scale directional Contourlet transform framework, leveraging high-frequency structural priors to guide the denoising trajectory—thereby jointly optimizing low-frequency statistical modeling and multi-scale directional feature representation. The method integrates complex Contourlet decomposition, knowledge-driven complex diffusion networks, and a multi-scale feature fusion mechanism. Evaluated on three real-world PolSAR datasets, it achieves significant improvements in classification accuracy (+2.3% average), edge fidelity, and regional consistency, outperforming current state-of-the-art methods.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Diffusion models have demonstrated exceptional performance across various domains due to their ability to model and generate complicated data distributions. However, when applied to PolSAR data, traditional real-valued diffusion models face challenges in capturing complex-valued phase information.Moreover, these models often struggle to preserve fine structural details. To address these limitations, we leverage the Contourlet transform, which provides rich multiscale and multidirectional representations well-suited for PolSAR imagery. We propose a structural knowledge-guided complex diffusion model for PolSAR image classification in the Contourlet domain. Specifically, the complex Contourlet transform is first applied to decompose the data into low- and high-frequency subbands, enabling the extraction of statistical and boundary features. A knowledge-guided complex diffusion network is then designed to model the statistical properties of the low-frequency components. During the process, structural information from high-frequency coefficients is utilized to guide the diffusion process, improving edge preservation. Furthermore, multiscale and multidirectional high-frequency features are jointly learned to further boost classification accuracy. Experimental results on three real-world PolSAR datasets demonstrate that our approach surpasses state-of-the-art methods, particularly in preserving edge details and maintaining region homogeneity in complex terrain.

Problem

• Capturing complex-valued phase information in PolSAR data
• Preserving fine structural details in PolSAR imagery
• Improving edge preservation and region homogeneity in classification

Innovation

• Contourlet transform for multiscale representation
• Complex diffusion model for phase information
• Knowledge-guided diffusion for edge preservation