研究人员开发了一个知识蒸馏框架，以提高边缘硬件上用于汽车安全的目标检测模型的性能。该方法训练了一个较小的YOLOv8-S模型来复制一个较大的YOLOv8-L模型的行为，实现了3.9倍的压缩。蒸馏后的模型在INT8量化方面表现出显著的鲁棒性，在这些约束条件下性能优于原始的较大模型，并将误报减少了44%。这种方法对于在资源受限的边缘设备上部署准确、安全关键的系统至关重要。 AI
影响 在资源受限的汽车边缘设备上实现更准确、更鲁棒的AI安全系统。
排序理由 学术论文，详细介绍了一种新的模型压缩和量化鲁棒性方法。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2604.26857v1 Announce Type: new Abstract: Deploying accurate object detection for Vulnerable Road User (VRU) safety on edge hardware requires balancing model capacity against computational constraints. Large models achieve high accuracy but fail under INT8 quantization requ…
Deploying accurate object detection for Vulnerable Road User (VRU) safety on edge hardware requires balancing model capacity against computational constraints. Large models achieve high accuracy but fail under INT8 quantization required for edge deployment, while small models sac…