HSCP: A Two-Stage Spectral Clustering Framework for Resource-Constrained UAV Identification

TL;DR

This paper introduces HSCP, a spectral clustering-based pruning framework that significantly compresses deep learning models for UAV identification, achieving high accuracy, robustness, and efficiency on resource-limited devices.

Contribution

HSCP uniquely combines layer and channel pruning guided by spectral clustering and CKA, optimizing model compression and performance for UAV RF fingerprint recognition.

Findings

Achieves 86.39% parameter reduction and 84.44% FLOPs reduction.

Improves accuracy by 1.49% over unpruned models.

Maintains robustness in low SNR environments.

Abstract

With the rapid development of Unmanned Aerial Vehicles (UAVs) and the increasing complexity of low-altitude security threats, traditional UAV identification methods struggle to extract reliable signal features and meet real-time requirements in complex environments. Recently, deep learning based Radio Frequency Fingerprint Identification (RFFI) approaches have greatly improved recognition accuracy. However, their large model sizes and high computational demands hinder deployment on resource-constrained edge devices. While model pruning offers a general solution for complexity reduction, existing weight, channel, and layer pruning techniques struggle to concurrently optimize compression rate, hardware acceleration, and recognition accuracy. To this end, in this paper, we introduce HSCP, a Hierarchical Spectral Clustering Pruning framework that combines layer pruning with channel pruning to achieve extreme compression, high performance, and efficient inference. In the first stage, HSCP employs spectral clustering guided by Centered Kernel Alignment (CKA) to identify and remove redundant layers. Subsequently, the same strategy is applied to the channel dimension to eliminate a finer redundancy. To ensure robustness, we further employ a noise-robust fine-tuning strategy. Experiments on the UAV-M100 benchmark demonstrate that HSCP outperforms existing channel and layer pruning methods. Specifically, HSCP achieves $86.39\%$ parameter reduction and $84.44\%$ FLOPs reduction on ResNet18 while improving accuracy by $1.49\%$ compared to the unpruned baseline, and maintains superior robustness even in low signal-to-noise ratio environments.