提出多权重自匹配方法，让CNN在雷达图像中更懂自己为何做出判断。
A multi-weight self-matching visual explanation for cnns on sar images
- 用特征图与梯度结合通道和元素级权重，可视化模型决策依据。
- 在自建雷达数据集上定位更准，能捕捉目标细节特征。
- 适合需要解释性的雷达图像分类与弱监督定位任务。
近年来，卷积神经网络（CNN）在合成孔径雷达（SAR）各类任务中取得显著进展。然而，其内部机制复杂且不透明，难以满足高可靠性要求，限制了在SAR领域的应用。提升CNN的可解释性对推动其在SAR中的发展与部署至关重要。本文提出一种名为多权重自匹配类激活映射（MS-CAM）的可视化解释方法。MS-CAM将SAR图像与CNN提取的特征图及对应梯度进行匹配，结合通道级与元素级权重，以可视化模型在SAR图像中学习到的决策依据。在自建的SAR目标分类数据集上进行的大量实验表明，MS-CAM能更准确地突出网络关注区域，并捕捉到目标的详细特征信息，从而增强模型可解释性。此外，验证了将MS-CAM应用于弱监督目标定位的可行性，并深入分析了像素阈值等影响定位精度的关键因素，为后续研究提供参考。
原文摘要 · Abstract (English)
In recent years, convolutional neural networks (CNNs) have achieved significant success in various synthetic aperture radar (SAR) tasks. However, the complexity and opacity of their internal mechanisms hinder the fulfillment of high-reliability requirements, thereby limiting their application in SAR. Improving the interpretability of CNNs is thus of great importance for their development and deployment in SAR. In this paper, a visual explanation method termed multi-weight self-matching class activation mapping (MS-CAM) is proposed. MS-CAM matches SAR images with the feature maps and corresponding gradients extracted by the CNN, and combines both channel-wise and element-wise weights to visualize the decision basis learned by the model in SAR images. Extensive experiments conducted on a self-constructed SAR target classification dataset demonstrate that MS-CAM more accurately highlights the network's regions of interest and captures detailed target feature information, thereby enhancing network interpretability. Furthermore, the feasibility of applying MS-CAM to weakly-supervised obiect localization is validated. Key factors affecting localization accuracy, such as pixel thresholds, are analyzed in depth to inform future work.
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。