让边缘设备实时更新视频模型，效率提升10倍
Legilimens: Performant Video Analytics on the System-on-Chip Edge
- 利用场景嵌入重叠性，轻量级适配新环境
- 重训成本降低2.8-10倍，准确率提升18-45%
- 适合无人机、行车记录仪等移动边缘设备
持续训练已成为提升边缘设备视频分析精度的核心手段。然而，现有系统依赖传统边缘服务器的闲置算力资源，而无人机、行车记录仪等移动边缘设备具有较弱算力但充足的统一内存。本文提出Legilimens，一种面向移动边缘SoC GPU的持续学习系统。核心洞察是：视觉差异显著的场景在模型嵌入上存在大量重叠；若将基础模型驻留设备内存，针对新场景的专项训练可仅需极少样本。为实现该思路，Legilimens提出三项高效技术：(1) 高效选择高价值数据样本用于再训练，(2) 无需完整重训即可更新基础模型，(3) 动态时间共享计算资源，兼顾再训练与实时推理。在多种工作负载下，相比现有系统，重训成本降低2.8-10倍，准确率提升18-45%。
原文摘要 · Abstract (English)
Continually retraining models has emerged as a primary technique to enable high-accuracy video analytics on edge devices. Yet, existing systems employ such adaptation by relying on the spare compute resources that traditional (memory-constrained) edge servers afford. In contrast, mobile edge devices such as drones and dashcams offer a fundamentally different resource profile: weak(er) compute with abundant unified memory pools. We present Legilimens, a continuous learning system for the mobile edge's System-on-Chip GPUs. Our driving insight is that visually distinct scenes that require retraining exhibit substantial overlap in model embeddings; if captured into a base model on device memory, specializing to each new scene can become lightweight, requiring very few samples. To practically realize this approach, Legilimens presents new, compute-efficient techniques to (1) select high-utility data samples for retraining specialized models, (2) update the base model without complete retraining, and (3) time-share compute resources between retraining and live inference for maximal accuracy. Across diverse workloads, Legilimens lowers retraining costs by 2.8-10x compared to existing systems, resulting in 18-45% higher accuracies.
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。