针对SAR图像特点改进对比学习，提升小模型分类性能。
PCM-SAR: Physics-Driven Contrastive Mutual Learning for SAR Classification
- 结合物理特性生成更真实的SAR样本，提升数据多样性。
- 多层级互学习融合特征，显著提升小模型表现。
- 适用于资源受限场景的高精度SAR图像分类任务。
基于对比学习的现有SAR图像分类方法常沿用光学图像的样本生成策略，未能充分捕捉SAR数据独特的语义与物理特性。为此，本文提出面向SAR分类的物理驱动对比互学习方法（PCM-SAR），通过引入领域特定的物理知识改进样本生成与特征提取。PCM-SAR利用灰度共生矩阵（GLCM）模拟真实的噪声模式，并采用语义检测实现无监督局部采样，确保生成样本准确反映SAR成像特性。此外，基于互学习的多层级特征融合机制可协同优化特征表示。实验表明，该方法在多个数据集和任务上持续优于当前最优方法，尤其显著提升了小型模型的性能，有效弥补其容量不足的问题。
原文摘要 · Abstract (English)
Existing SAR image classification methods based on Contrastive Learning often rely on sample generation strategies designed for optical images, failing to capture the distinct semantic and physical characteristics of SAR data. To address this, we propose Physics-Driven Contrastive Mutual Learning for SAR Classification (PCM-SAR), which incorporates domain-specific physical insights to improve sample generation and feature extraction. PCM-SAR utilizes the gray-level co-occurrence matrix (GLCM) to simulate realistic noise patterns and applies semantic detection for unsupervised local sampling, ensuring generated samples accurately reflect SAR imaging properties. Additionally, a multi-level feature fusion mechanism based on mutual learning enables collaborative refinement of feature representations. Notably, PCM-SAR significantly enhances smaller models by refining SAR feature representations, compensating for their limited capacity. Experimental results show that PCM-SAR consistently outperforms SOTA methods across diverse datasets and SAR classification tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。