用注意力机制提升雷达图像目标识别准确率与鲁棒性
Studying the Effects of Self-Attention on SAR Automatic Target Recognition
- 引入注意力模块聚焦车辆阴影等关键特征
- 在MSTAR数据集上提升顶1准确率，增强抗噪能力
- 结果更可解释，适合需要可信AI的军事应用
注意力机制在合成孔径雷达（SAR）自动目标识别（ATR）系统发展中至关重要。传统SAR ATR模型常受噪声干扰，误学背景信息而非关键特征。注意力机制通过动态聚焦阴影、车辆小部件等重要区域，仅用少数像素即可表征全图，显著提升分类精度。该方法有效区分目标与杂波，使模型更具实用性与鲁棒性。实验表明，注意力模块在MSTAR数据集上提升了顶1准确率，增强了输入鲁棒性，并具备更强的可解释性。
原文摘要 · Abstract (English)
Attention mechanisms are critically important in the advancement of synthetic aperture radar (SAR) automatic target recognition (ATR) systems. Traditional SAR ATR models often struggle with the noisy nature of the SAR data, frequently learning from background noise rather than the most relevant image features. Attention mechanisms address this limitation by focusing on crucial image components, such as the shadows and small parts of a vehicle, which are crucial for accurate target classification. By dynamically prioritizing these significant features, attention-based models can efficiently characterize the entire image with a few pixels, thus enhancing recognition performance. This capability allows for the discrimination of targets from background clutter, leading to more practical and robust SAR ATR models. We show that attention modules increase top-1 accuracy, improve input robustness, and are qualitatively more explainable on the MSTAR dataset.
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。