Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-Domain Supervised Contrastive Learning for UAV Radio-Frequency Open-Set Recognition

Ning Gao, Tianrui Zeng, Bowen Chen, Donghong Cai, Shi Jin, Michail Matthaiou

TL;DR

This paper proposes a multi-domain supervised contrastive learning (MD-SupContrast) framework for UAV radio frequency (RF) open-set recognition, and proposes an improved generative OpenMax algorithm and construct an open-set recognition model, namely Open-RFNet.

Abstract

5G-Advanced (5G-A) has enabled the vibrant development of low altitude integrated sensing and communication (LA-ISAC) networks. As a core component of these networks, unmanned aerial vehicles (UAVs) have witnessed rapid growth in recent years. However, due to the lag in traditional industry regulatory norms, unauthorized flight incidents occur frequently, posing a severe security threat to LA-ISAC networks. To surveil the non-cooperative UAVs, in this paper, we propose a multi-domain supervised contrastive learning (MD-SupContrast) framework for UAV radio frequency (RF) open-set recognition. Specifically, first, the texture features and the time-frequency position features from the ResNet and the TransformerEncoder are fused, and then the supervised contrastive learning is applied to optimize the feature representation of the closed-set samples. Next, to surveil the invasive UAVs that appear in real life, we propose an improved generative OpenMax (IG-OpenMax) algorithm and construct an open-set recognition model, namely Open-RFNet. According to the unknown samples, we first freeze the feature extraction layers and then only retrain the classification layer, which achieves excellent recognition performance both in closed-set and open-set recognitions. We analyze the computational complexity of the proposed model. Experiments are conducted with a large-scale UAV open dataset. The results show that the proposed Open-RFNet outperforms the existing benchmark methods in terms of recognition accuracy between the known and the unknown UAVs, as it achieves 95.12% in closed-set and 96.08% in open-set under 25 UAV types, respectively.

Multi-Domain Supervised Contrastive Learning for UAV Radio-Frequency Open-Set Recognition

TL;DR

This paper proposes a multi-domain supervised contrastive learning (MD-SupContrast) framework for UAV radio frequency (RF) open-set recognition, and proposes an improved generative OpenMax algorithm and construct an open-set recognition model, namely Open-RFNet.

Abstract

5G-Advanced (5G-A) has enabled the vibrant development of low altitude integrated sensing and communication (LA-ISAC) networks. As a core component of these networks, unmanned aerial vehicles (UAVs) have witnessed rapid growth in recent years. However, due to the lag in traditional industry regulatory norms, unauthorized flight incidents occur frequently, posing a severe security threat to LA-ISAC networks. To surveil the non-cooperative UAVs, in this paper, we propose a multi-domain supervised contrastive learning (MD-SupContrast) framework for UAV radio frequency (RF) open-set recognition. Specifically, first, the texture features and the time-frequency position features from the ResNet and the TransformerEncoder are fused, and then the supervised contrastive learning is applied to optimize the feature representation of the closed-set samples. Next, to surveil the invasive UAVs that appear in real life, we propose an improved generative OpenMax (IG-OpenMax) algorithm and construct an open-set recognition model, namely Open-RFNet. According to the unknown samples, we first freeze the feature extraction layers and then only retrain the classification layer, which achieves excellent recognition performance both in closed-set and open-set recognitions. We analyze the computational complexity of the proposed model. Experiments are conducted with a large-scale UAV open dataset. The results show that the proposed Open-RFNet outperforms the existing benchmark methods in terms of recognition accuracy between the known and the unknown UAVs, as it achieves 95.12% in closed-set and 96.08% in open-set under 25 UAV types, respectively.

Paper Structure

This paper contains 27 sections, 36 equations, 7 figures, 8 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Background
  3. Motivation and Contribution
  4. Overview
  5. Related Work
  6. RF recognition methods
  7. Other recognition methods
  8. Open-set recognition
  9. Preliminaries
  10. Training Framework and Model
  11. Data Preprocessing
  12. closed-set Recognition
  13. Feature Extraction
  14. Supervised Contrastive Learning
  15. Open-set Recognition
  16. ...and 12 more sections

Figures (7)

  • Figure 1: The schematic diagram of a UAV RF signal.
  • Figure 2: The constructed Open-RFNet model based on the proposed MD-SupContrast framework.
  • Figure 3: Air-to-ground LoS sensing link between the UAV and the base station.
  • Figure 4: Training loss with respect to the epoch.
  • Figure 5: Visualization of the distribution of known classifications.
  • ...and 2 more figures

Theorems & Definitions (3)

  • Remark
  • Remark
  • Remark