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

arXiv: https://arxiv.org/abs/2512.08983 · HTML: https://mlsanity.com/paper/2512.08983/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 74 references that are in the map.
- First posted on arXiv 5 Dec 2025.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [HRank: Filter Pruning using High-Rank Feature Map](https://mlsanity.com/paper/2002.10179/) (2020)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [Over the Air Deep Learning Based Radio Signal Classification](https://mlsanity.com/paper/1712.04578/) (2017)
- [Vision Meets Drones: A Challenge](https://mlsanity.com/paper/1804.07437/) (2018)
- [SepPrune: Structured Pruning for Efficient Deep Speech Separation](https://mlsanity.com/paper/2505.12079/) (2025)
- [ORACLE: Optimized Radio clAssification through Convolutional neuraL nEtworks](https://mlsanity.com/paper/1812.01124/) (2018)
- [Understanding the Dynamics of DNNs Using Graph Modularity](https://mlsanity.com/paper/2111.12485/) (2021)
- [Reassessing Layer Pruning in LLMs: New Insights and Methods](https://mlsanity.com/paper/2411.15558/) (2024)
- [A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models](https://mlsanity.com/paper/2406.07929/) (2024)
- [SR-init: An interpretable layer pruning method](https://mlsanity.com/paper/2303.07677/) (2023)
- [Micro-UAV Detection and Classification from RF Fingerprints Using Machine Learning Techniques](https://mlsanity.com/paper/1901.07703/) (2019)
- [Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue Summarization](https://mlsanity.com/paper/2507.02145/) (2025)
- [A multi-task learning for cavitation detection and cavitation intensity recognition of valve acoustic signals](https://mlsanity.com/paper/2203.01118/) (2022)
- [Few-Shot Specific Emitter Identification via Deep Metric Ensemble Learning](https://mlsanity.com/paper/2207.06592/) (2022)
- [An acoustic signal cavitation detection framework based on XGBoost with adaptive selection feature engineering](https://mlsanity.com/paper/2202.13226/) (2022)
- [The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models](https://mlsanity.com/paper/2510.23652/) (2025)
- [Securing UAV Communications by Fusing Cross-Layer Fingerprints](https://mlsanity.com/paper/2511.05796/) (2025)

## Abstract (arXiv)

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.