AI 中文总结
研究合成孔径声呐数据自动目标识别中训练深度神经网络的问题，系统比较多种数据增强策略及与现代DNN架构结合的效果，发现增强能提高目标识别准确率但效果有差异。
AI 中文摘要
在这项工作中，我们研究了用于合成孔径声呐（SAS）数据的自动目标识别（ATR），重点是深度神经网络（DNN）。在为SAS ATR训练DNN时，主要挑战源于标记目标示例数量有限，这是由于收集真实世界SAS数据所需的巨大成本和时间所致。一种成功缓解训练数据有限问题的通用策略是增强，即通过对可用真实世界数据引入现实变化来生成额外的合成训练数据。先前研究已探讨了多种用于SAS ATR的增强策略，包括传统图像增强（如对比度变化、裁剪）以及基于物理的增强。基于先前工作，我们系统地比较了许多现有增强策略用于为SAS ATR训练DNN。我们还研究了增强与现代DNN架构（如变压器）结合时的影响。结果表明增强可提高目标识别准确率，尽管益处各异，且并非所有增强都有益。
英文摘要
In this work we study Automatic Target Recognition (ATR) for Synthetic Aperture Sonar (SAS) data with a focus on deep neural networks (DNNs). The main challenge in training DNNs for SAS-ATR arises from the limited quantity of labeled target examples due to the significant costs and time required to collect real-world SAS data. One successful general strategy for mitigating the problem of limited training data is augmentation, which generates additional synthetic training data by introducing realistic variations to available data. Prior research has investigated a variety of augmentation strategies for SAS-ATR, including conventional image augmentations (e.g., contrast changes, cropping) as well as augmentations motivated the specific physics of SAS data. Building on prior work, we systematically compare many of these existing augmentation strategies for training DNNs for SAS-ATR. We also investigate the impact of augmentation when combined with modern DNN architectures such as transformers. The results indicate that augmentation can improve target recognition accuracy, although benefits vary, and not all augmentations are beneficial.
CommentsThis paper was originally published in the proceedings of the International Conference on Underwater Acoustics 2026
