用脉冲神经网络实现高效车辆识别，准确率达94.8%。
DRiVE: Dynamic Recognition in VEhicles using snnTorch
- 基于snnTorch框架，利用脉冲神经元动态进行图像分类。
- 在车辆检测任务中达到94.8%准确率和0.99 AUC。
- 证明了脉冲网络在视觉任务中的潜力，适合低功耗场景。
脉冲神经网络（SNNs）通过事件驱动机制模拟生物大脑活动，仅在输入超过阈值时激活神经元，利用膜电位动态有效保留时间信息。本研究结合PyTorch的可扩展框架snnTorch，探索SNN在图像任务中的应用。提出DRiVE模型，利用脉冲神经元动力学对图像进行分类，在车辆检测任务中取得94.8%的准确率和0.99的AUC分数。结果表明，DRiVE能有效区分车辆类别，挑战了传统认为SNN仅适用于时序数据的观点。随着对节能神经模型的需求上升，该工作凸显了优化SNN以应用于视觉任务的重要性，并推动其在高精度与低功耗并重的实际场景中的进一步探索。
原文摘要 · Abstract (English)
Spiking Neural Networks (SNNs) mimic biological brain activity, processing data efficiently through an event-driven design, wherein the neurons activate only when inputs exceed specific thresholds. Their ability to track voltage changes over time via membrane potential dynamics helps retain temporal information. This study combines SNNs with PyTorch's adaptable framework, snnTorch, to test their potential for image-based tasks. We introduce DRiVE, a vehicle detection model that uses spiking neuron dynamics to classify images, achieving 94.8% accuracy and a near-perfect 0.99 AUC score. These results highlight DRiVE's ability to distinguish vehicle classes effectively, challenging the notion that SNNs are limited to temporal data. As interest grows in energy-efficient neural models, DRiVE's success emphasizes the need to refine SNN optimization for visual tasks. This work encourages broader exploration of SNNs in scenarios where conventional networks struggle, particularly for real-world applications requiring both precision and efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。