发表机构
Electronics and Telecommunications Research Institute (ETRI); Jeonbuk National University（电子与电信研究所（ETRI）; 全北国立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对异构边缘平台多摄像头流式感知，本文指出孤立评估会错误排序加速器放置，提出评估应报告争用扫描、截止时间错失率和最差流sAP，以揭示平均sAP隐藏的单流退化。
AI 中文摘要
多摄像头流式感知日益部署在与共驻工作负载共享的异构边缘平台上，然而加速器放置通常通过孤立的单流实验和平均流式平均精度（sAP）进行评估。利用单GPU-NPU平台上的两个端到端流水线，我们表明孤立评估可能对部署时的放置进行错误排序。尽管GPU流水线在孤立情况下更受青睐，但GPU局部化争用引入了截止时间错失，使检测变得过时，并可能在GPU完全饱和之前反转首选放置。NPU流水线在孤立情况下对小物体和中物体的精度低于GPU流水线，但在大物体上几乎与之匹配。在我们延迟和争用实验中，最大的绝对sAP损失发生在大物体上。在我们的四流实验中，首选放置取决于哪条路径变得过时，增加GPU侧争用将最佳放置从全GPU转移到全NPU。在GPU饱和的视觉-语言共租户下，全NPU的最差流sAP达到全GPU的5.2倍。由于平均sAP可能隐藏严重的单流退化，评估应报告争用扫描、两条路径上的截止时间错失率以及最差流sAP，同时报告平均sAP。
英文摘要
Multi-camera streaming perception is increasingly deployed on heterogeneous edge platforms shared with co-resident workloads, yet accelerator placement is often evaluated using isolated single-stream experiments and mean streaming average precision (sAP). Using two end-to-end pipelines on a single GPU--NPU platform, we show that isolated evaluation can mis-rank deployment-time placement. Although the GPU pipeline is preferred in isolation, GPU-localized contention introduces deadline misses that make detections stale and can reverse the preferred placement before full GPU saturation. The NPU pipeline is less accurate than the GPU pipeline on small and medium objects in isolation, but nearly matches it on large objects. The largest absolute sAP losses in our latency and contention experiments occur for large objects. In our four-stream experiments, the preferred placement depends on which path becomes stale, and increasing GPU-side contention shifts the best placement from All-GPU to All-NPU. Under a GPU-saturating vision--language co-tenant, All-NPU achieves $5.2\times$ the worst-stream sAP of All-GPU. Because mean sAP can hide severe single-stream degradation, evaluation should report contention sweeps, deadline-miss rates on both paths, and worst-stream sAP alongside mean sAP.
Commentsaccepted in ACCV 2026
