Instance-Wise Feature Selection for UAV Classification Based on Radar Micro-Doppler Signatures

Unmanned aerial vehicle (UAV) classification using radar micro-Doppler signatures remains challenging due to the diversity, variability, and heterogeneity of the observed features. Most existing feature selection methods adopt a global strategy, which overlooks sample-specific differences arising from diverse UAV categories, flight dynamics, and observation conditions. To address this limitation, we propose an instance-wise feature selection framework based on the Information Bottleneck (IB)principle. The method jointly optimizes a differentiable feature selector and a classifier via variational inference and Gumbel–Softmax reparameterization, enabling adaptive identification of discriminative features for each sample. Experimental evaluations on real radar data validate the effectiveness and interpretability of the proposed approach.