轻量级零样本异常检测模型，可直接部署于边缘设备
EdgeZSAD: Practical Zero-Shot Anomaly Detection on Edge Devices
- 采用2100万参数的TinyViT骨干网络，适配嵌入式硬件
- 在MVTec-AD上达到91.6的图像AUROC，VisA达88.2
- 支持Jetson和RB5设备直接部署，性能稳定无显著漂移
工业质检需要在边缘部署约束下实现零样本异常检测（ZSAD）。现有方法常依赖参数量约3亿的ViT-L主干网络，超出典型嵌入式硬件的内存与算力预算。本文提出EdgeZSAD，基于TinyViT-21M-512主干网络、非对称全局-局部读出机制（EdgeGLR）及可复现的源端训练方案（Real-IAD-DR），在单个源训练目标未见协议下训练一个检查点，并在六个工业基准上评估。三次独立实验中，模型在MVTec-AD上的平均图像AUROC达91.6，在VisA上为88.2；且可直接部署于Jetson Orin Nano Super（TensorRT FP16）与RB5 Gen2（QNN GPU FP16）平台。在六个设备重评分基准上，图像AUROC漂移低于0.2点，表明导出图在部署环境下保持了主机端排序行为。
原文摘要 · Abstract (English)
Industrial inspection needs zero-shot anomaly detection (ZSAD) that remains useful under edge deployment constraints. Recent methods often rely on ViT-L foundation backbones (~300M parameters), which exceed the memory and operator budget of typical embedded hardware. We study this regime through EdgeZSAD, a compact reference system built around a TinyViT-21M-512 backbone, an asymmetric global-local readout (EdgeGLR), and a reproducible source-side training recipe (Real-IAD-DR). We train a single checkpoint in a source-trained, target-unseen protocol and evaluate it across six industrial benchmarks. Across three independent runs, the resulting model reaches an average image AUROC of 91.6 on MVTec-AD and 88.2 on VisA, while remaining directly deployable on Jetson Orin Nano Super (TensorRT FP16) and RB5 Gen2 (QNN GPU FP16). Across the six device-rescored benchmarks, image-AUROC drift stays below 0.2 points, indicating that the exported graph preserves host-side ranking behavior in the evaluated deployment setting.
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。