15,500 Seconds: Lean UAV Classification Using EfficientNet and Lightweight Fine-Tuning

TL;DR

This paper demonstrates that lightweight EfficientNet models combined with parameter-efficient fine-tuning and data augmentation can achieve high accuracy in UAV audio classification with limited data, outperforming other architectures.

Contribution

It introduces a novel approach integrating EfficientNet with PEFT and augmentation for UAV audio classification, addressing data scarcity challenges.

Findings

EfficientNet-B0 with three augmentations achieved 95.95% accuracy.

Full fine-tuning outperformed partial fine-tuning and other models.

Lightweight architectures with PEFT are effective for limited UAV audio datasets.

Abstract

As unmanned aerial vehicles (UAVs) become increasingly prevalent in both consumer and defense applications, the need for reliable, modality-specific classification systems grows in urgency. This paper addresses the challenge of data scarcity in UAV audio classification by expanding on prior work through the integration of pre-trained deep learning models, parameter-efficient fine-tuning (PEFT) strategies, and targeted data augmentation techniques. Using a custom dataset of 3,100 UAV audio clips (15,500 seconds) spanning 31 distinct drone types, we evaluate the performance of transformer-based and convolutional neural network (CNN) architectures under various fine-tuning configurations. Experiments were conducted with five-fold cross-validation, assessing accuracy, training efficiency, and robustness. Results show that full fine-tuning of the EfficientNet-B0 model with three augmentations achieved the highest validation accuracy (95.95), outperforming both the custom CNN and transformer-based models like AST. These findings suggest that combining lightweight architectures with PEFT and well-chosen augmentations provides an effective strategy for UAV audio classification on limited datasets. Future work will extend this framework to multimodal UAV classification using visual and radar telemetry.