QDS-SNN: Energy-efficient Quantum Deeply-Supervised Spiking Neural Network Algorithm for Traffic Sign Recognition

2026-06-03

AI Summary

This work addresses the limitations of conventional traffic sign recognition methods, which rely heavily on large-scale datasets and high computational resources, thereby compromising real-time performance and energy efficiency. Existing spiking neural networks (SNNs) further suffer from information loss and vanishing gradients. To overcome these challenges, this study introduces a novel architecture that integrates quantum neural networks into a deeply supervised SNN framework, featuring temporally and spatially adaptive LIF neurons (TSA-LIF) and a quantum-assisted classification module (QACM). By leveraging quantum superposition, entanglement, and parallelism, the proposed model significantly enhances representational capacity, training stability, and recognition accuracy. Evaluated on the GTSRB and TSRD datasets, the model achieves 99.72% and 97.90% accuracy, respectively, using only six time steps—outperforming the MS-ResNet baseline by 1.32% and 1.25% while reducing energy consumption by over 47.32%.

Abstract

Traffic sign recognition is crucial for intelligent transportation and autonomous driving, as it can improve driving efficiency and ensure road safety. However, traditional recognition methods are based on large datasets and intensive computation, which limits their real-time applicability. Spiking Neural Networks (SNNs) offer a biologically inspired, energy-efficient alternative due to their spatiotemporal processing capabilities, but suffer from information loss and vanishing gradients during training. To overcome these limitations, this study proposes a Quantum Deep-supervised Spiking Neural Network (QDS-SNN) that integrates Quantum Neural Networks (QNNs) for efficient, low-power deep supervision. Using quantum superposition and entanglement, QNNs enable expressive representations and parallel computation, thereby enhancing performance without compromising energy efficiency. The proposed QDS-SNN incorporates a temporally and spatially adaptive LIF (TSA-LIF) neuron and a quantum-assisted classifier module (QACM) to mitigate gradient issues and improve training effectiveness. This study conducts experiments on the PennyLane quantum simulation platform, and the results show that QDS-SNN achieves 99.72\% accuracy on the GTSRB dataset in only 6 time steps -- outperforming the MS-ResNet baseline by 1.32\% while reducing energy consumption by 55.77\%. In the TSRD dataset, it achieves 97.90\% accuracy while reducing energy use to 52.68\% of the baseline. These results demonstrate that QDS-SNN offers a high-performance, energy-efficient solution for traffic sign recognition in intelligent transportation systems.

Problem

• Traffic Sign Recognition
• Spiking Neural Networks
• Energy Efficiency
• Gradient Vanishing
• Real-time Applicability

Innovation

• Quantum Neural Networks
• Spiking Neural Networks
• Deep Supervision
• Energy Efficiency
• Traffic Sign Recognition