PASTE: Physics-Aware Scattering Topology Embedding Framework for SAR Object Detection

2026-03-16

AI Summary

This work addresses the limitation of existing SAR target detection methods, which often adopt strategies designed for optical imagery and neglect the underlying electromagnetic scattering mechanisms, thereby failing to exploit valuable scattering topology information. To bridge this gap, the authors propose a physics-driven, end-to-end framework that leverages the Attributed Scattering Center (ASC) model to automatically generate scattering keypoints. A dedicated topological injection module and a prior-aware supervision strategy are introduced to embed scattering priors into modern detection architectures. By integrating multi-scale feature guidance with alignment of scattering center distributions, the method achieves consistent performance gains across multiple real-world datasets, improving mAP by 2.9%–11.3% over baseline detectors while maintaining manageable computational overhead. Visualization results further confirm the effectiveness of the incorporated scattering priors and enhance model interpretability.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Current deep learning-based object detection for Synthetic Aperture Radar (SAR) imagery mainly adopts optical image methods, treating targets as texture patches while ignoring inherent electromagnetic scattering mechanisms. Though scattering points have been studied to boost detection performance, most methods still rely on amplitude-based statistical models. Some approaches introduce frequency-domain information for scattering center extraction, but they suffer from high computation cost and poor compatibility with diverse datasets. Thus, effectively embedding scattering topological information into modern detection frameworks remains challenging. To solve these problems, this paper proposes the Physics-Aware Scattering Topology Embedding Framework (PASTE), a novel closed-loop architecture for comprehensive scattering prior integration. By building the full pipeline from topology generation, injection to joint supervision, PASTE elegantly integrates scattering physics into modern SAR detectors. Specifically, it designs a scattering keypoint generation and automatic annotation scheme based on the Attributed Scattering Center (ASC) model to produce scalable and physically consistent priors. A scattering topology injection module guides multi-scale feature learning, and a scattering prior supervision strategy constrains network optimization by aligning predictions with scattering center distributions. Experiments on real datasets show that PASTE is compatible with various detectors and brings relative mAP gains of 2.9% to 11.3% over baselines with acceptable computation overhead. Visualization of scattering maps verifies that PASTE successfully embeds scattering topological priors into feature space, clearly distinguishing target and background scattering regions, thus providing strong interpretability for results.

Problem

• SAR object detection
• scattering topology
• electromagnetic scattering mechanisms
• scattering center
• deep learning

Innovation

• Scattering Topology
• Physics-Aware Embedding
• SAR Object Detection
• Attributed Scattering Center
• Feature Injection