DIALER：在免重训练的边缘视频分析中提升稀有类准确率的案例研究

中文摘要 AI 辅助

使用轻量级模型的边缘视频分析容易因实时视频流中的持续分布偏移而出现准确率下降。虽然持续学习（CL）能够应对此类数据漂移，但它会严重消耗原本为推理而配置的边缘服务器的有限计算资源。我们的实证研究表明，新兴的视觉基础模型（VFM）提供了一种实用的免重训练替代方案，能够以显著的计算节省实现高平均准确率。然而，VFM 经常将特定稀有类（通常代表关键对象）误分类为视觉上相似的常见类。我们设计了 DIALER 系统，利用免重训练 VFM 推理释放的空闲计算周期来缓解稀有类误分类问题。具体而言，DIALER 离线预构建针对主要稀有类到常见类混淆对的多阶段纠正流水线。在运行时，它将纠正候选路由到相应的流水线，并根据空闲 GPU 余量执行尽可能多的阶段。在四个真实世界驾驶数据集上的评估表明，DIALER 在不干扰多流分析实时 VFM 推理的情况下，将稀有类准确率提升了高达 14.0%。

英文摘要

Edge video analytics with lightweight models is prone to accuracy degradation due to persistent distributional shifts in live video streams. While continuous learning (CL) addresses such data drift, it heavily strains the limited compute resources of edge servers originally provisioned for inference. Our empirical study reveals that emerging vision foundation models (VFMs) offer a practical, retraining-free alternative that delivers high average accuracy with remarkable compute savings. However, VFMs frequently misclassify specific rare classes, which often represent critical objects, as visually similar common classes. We design DIALER, a system that exploits the spare compute cycles freed by retraining-free VFM inference to mitigate rare-class misclassifications. Specifically, DIALER pre-builds multi-stage correction pipelines for dominant rare-to-common confusion pairs offline. At runtime, it routes correction candidates to the corresponding pipelines and executes as many stages as idle GPU headroom permits. Evaluation on four real-world driving datasets shows that DIALER improves rare-class accuracy by up to 14.0% without interfering with real-time VFM inference for multi-stream analytics.

发表机构

• POSTECH（浦项科技大学）
• Seoul National University（首尔大学）
• University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

机构由 AI 辅助整理，请以论文原文为准。