ROSAR：一种用于鲁棒侧扫声纳目标检测的对抗性重训练框架
ROSAR: An Adversarial Re-Training Framework for Robust Side-Scan Sonar Object Detection
AI总结：
本文提出ROSAR框架，通过结合知识蒸馏与对抗性重训练，并引入三个公开SSS数据集和两个安全属性，有效提升了侧扫声纳目标检测模型在特定噪声条件下的鲁棒性和检测精度。
摘要：
本文介绍了ROSAR，这是一种新颖的框架，旨在增强专为侧扫声纳（SSS）图像定制的深度学习目标检测模型的鲁棒性，这些图像由自主水下航行器使用声纳传感器生成。通过扩展我们先前在知识蒸馏（KD）方面的工作，该框架将KD与对抗性重训练相结合，以应对模型效率和针对SSS噪声的鲁棒性双重挑战。我们引入了三个公开可用的SSS数据集，捕获了不同的声纳设置和噪声条件。我们提出并形式化了两个SSS安全属性，并利用它们生成用于重训练的对抗性数据集。通过对投影梯度下降（PGD）和基于补丁的对抗性攻击进行比较分析，ROSAR在SSS特定条件下显著提升了模型鲁棒性和检测精度，将模型的鲁棒性提高了1.85%。ROSAR可在https://github.com/remaro-network/ROSAR-framework获取。
英文摘要：
This paper introduces ROSAR, a novel framework enhancing the robustness of deep learning object detection models tailored for side-scan sonar (SSS) images, generated by autonomous underwater vehicles using sonar sensors. By extending our prior work on knowledge distillation (KD), this framework integrates KD with adversarial retraining to address the dual challenges of model efficiency and robustness against SSS noises. We introduce three novel, publicly available SSS datasets, capturing different sonar setups and noise conditions. We propose and formalize two SSS safety properties and utilize them to generate adversarial datasets for retraining. Through a comparative analysis of projected gradient descent (PGD) and patch-based adversarial attacks, ROSAR demonstrates significant improvements in model robustness and detection accuracy under SSS-specific conditions, enhancing the model's robustness by up to 1.85%. ROSAR is available at https://github.com/remaro-network/ROSAR-framework.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
