arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.18329cs.LG
收藏

基于梯度范数的判别性驱动的空域-通道选择用于无人机信号OOD检测

Discriminability-Driven Spatial-Channel Selection with Gradient Norm for Drone Signal OOD Detection

State Key Laboratory of Integrated Services Network(信息服务网络国家重点实验室);Xidian University(西安电子科技大学)

Chuhan Feng, Jing Li, Jie Li, Lu Lv, Fengkui Gong

AI总结:

本文提出了一种结合判别性驱动空域-通道选择和梯度范数的无人机信号OOD检测算法,通过自适应加权时间-频率特征和融合能量分数,提升检测的判别力和鲁棒性。

摘要:

我们提出了一种基于判别性驱动的空域-通道选择和梯度范数的无人机信号Out-of-Distribution(OOD)检测算法。通过量化协议特定的时间-频率特性,时间-频率图像特征在空间和通道维度上被自适应加权。随后,引入了梯度范数度量来衡量扰动敏感性,以捕捉OOD样本的内在不稳定性,该度量随后与基于能量的分数融合进行联合推断。仿真结果表明,所提出算法通过信噪比和各种无人机类型实现了优越的判别能力和鲁棒性能。

英文摘要:

We propose a drone signal out-of-distribution (OOD) detection algorithm based on discriminability-driven spatial-channel selection with a gradient norm. Time-frequency image features are adaptively weighted along both spatial and channel dimensions by quantifying inter-class similarity and variance based on protocol-specific time-frequency characteristics. Subsequently, a gradient-norm metric is introduced to measure perturbation sensitivity for capturing the inherent instability of OOD samples, which is then fused with energy-based scores for joint inference. Simulation results demonstrate that the proposed algorithm provides superior discriminative power and robust performance via SNR and various drone types.

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。

↑