Discriminability-Driven Spatial-Channel Selection with Gradient Norm for Drone Signal OOD Detection
This work addresses drone signal detection for security or monitoring applications, but it appears incremental as it builds on existing OOD detection methods with specific adaptations.
The paper tackled the problem of detecting out-of-distribution drone signals by proposing an algorithm that uses discriminability-driven spatial-channel selection and a gradient-norm metric, resulting in superior discriminative power and robust performance across different signal-to-noise ratios and drone types.
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.