发表机构
Intelligent Precision Instrument（智能精密仪器机构）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出用于工业异常检测的LUMIN网络，核心为零骨干前向传播的PSP采样流水线与两项推理优化，在5个基准上实现采样精度高、构建快且推理效率提升显著的效果。
AI 中文摘要
工业异常检测面临两大工程瓶颈：内存库构建延迟与推理效率。传统采样算法（最远点采样Farthest Point Sampling、K-Means等）依赖大量骨干网络前向传播与迭代距离计算，构建时间从数分钟到数小时不等；多尺度特征提取等繁重计算组件难以满足生产线毫秒级实时要求。本文针对工业部署的采样效率与推理优化展开研究，有两项核心贡献：（1）PSP（插件采样流水线）——基于18维像素元数据与5种互补视觉插件的四阶段自适应内存库采样流水线，PSP完成全部采样无需骨干网络前向传播；粗过滤为亚秒级数值排序，元数据提取为一次性离线成本，支持渐进式部署与增量更新。（2）两项工程优化策略——并行内存库相似度计算（将推理内存与延迟降低95%以上）与面向大规模评估的分层像素采样（在指标稳定的同时将计算时间减少20倍）。作为验证载体，本文引入经极端分割头压缩的LUMIN（轻量级通用制造检测网络），针对强基准系统地探索精度-效率前沿。在5个基准上的实验表明，PSP的采样精度达到当前最优水平，构建成本接近随机采样（比FPS快341倍），而推理优化将评估时间减少20倍且精度损失可忽略不计。
英文摘要
Industrial anomaly detection faces two engineering bottlenecks: memory bank construction latency and inference efficiency. Traditional sampling algorithms (Farthest Point Sampling, K-Means, etc.) rely on numerous backbone forward passes and iterative distance computations, with construction times ranging from minutes to hours; heavy computation components such as multi-scale feature extraction struggle to meet the millisecond-level real-time requirements of production lines. This paper focuses on sampling efficiency and inference optimization for industrial deployment with two core contributions: (1) PSP (Plugin Sampler Pipeline)---a four-stage adaptive memory bank sampling pipeline based on 18-dimensional pixel metadata and five complementary visual plugins. PSP completes all sampling with zero backbone forward passes; coarse filtering is sub-second numerical sorting, and metadata extraction is a one-time offline cost. PSP supports progressive deployment and incremental updates. (2) Two engineering optimization strategies---parallel memory bank similarity computation (reducing inference memory and latency by over 95\%) and stratified pixel sampling for large-scale evaluation (reducing computation time by 20$\times$ while keeping metrics stable). As a vehicle for validation, we introduce LUMIN (Lightweight Universal Manufacturing Inspection Network) with extreme segmentation-head compression, systematically exploring the accuracy-efficiency frontier against strong baselines. Experiments on five benchmarks demonstrate that PSP matches state-of-the-art sampling accuracy at near-random construction cost (341$\times$ faster than FPS), while inference optimizations reduce evaluation time by 20$\times$ with negligible accuracy loss.
Comments10 pages, 5 figures
