English(EN) Real-Time Frame- and Event-based Object Detection with Spiking Neural Networks on Edge Neuromorphic Hardware: Design, Deployment and Benchmark

英特尔 Loihi 2 上的脉冲神经网络实现能效高的实时目标检测

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-30 19:07

研究人员开发了一种在边缘神经形态硬件（特别是英特尔 Loihi 2 处理器）上为实时目标检测设计和部署脉冲神经网络（SNN）的方法。他们的工作表明，Loihi 2 上的 SNN 可以实现低能耗、实时的检测，在功耗方面优于传统的神经网络（ANN）。通过感知蒸馏的训练，SNN 在保持较低延迟的同时，恢复了 ANN 的大部分准确性，凸显了神经形态系统在能效高的边缘应用方面的潜力。 AI

影响展示了在边缘设备上实现高能效、实时目标检测的潜力，对机器人和自主系统产生影响。

排序理由学术论文，详细介绍了神经形态硬件上 SNN 的新方法论和基准测试。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Udayanga G. W. K. N. Gamage, Yan Zeng, Cesar Cadena, Matteo Fumagalli, Silvia Tolu · 2026-05-04 04:00

Real-Time Frame- and Event-based Object Detection with Spiking Neural Networks on Edge Neuromorphic Hardware: Design, Deployment and Benchmark

arXiv:2605.00146v1 Announce Type: new Abstract: Real-time object detection on energy-constrained platforms is critical for applications such as UAV-based inspection, autonomous navigation, and mobile robotics. Spiking neural networks (SNNs) on neuromorphic hardware are believed t…
arXiv cs.CV TIER_1 English(EN) · Silvia Tolu · 2026-04-30 19:07

Real-Time Frame- and Event-based Object Detection with Spiking Neural Networks on Edge Neuromorphic Hardware: Design, Deployment and Benchmark

Real-time object detection on energy-constrained platforms is critical for applications such as UAV-based inspection, autonomous navigation, and mobile robotics. Spiking neural networks (SNNs) on neuromorphic hardware are believed to be significantly more energy-efficient than co…

报道来源 [2]

Real-Time Frame- and Event-based Object Detection with Spiking Neural Networks on Edge Neuromorphic Hardware: Design, Deployment and Benchmark

Real-Time Frame- and Event-based Object Detection with Spiking Neural Networks on Edge Neuromorphic Hardware: Design, Deployment and Benchmark

相关实体

相关话题