用高效压缩提升物联网视觉异常检测的可扩展性
Towards Scalable IoT Deployment for Visual Anomaly Detection via Efficient Compression
- 采用轻量级数据压缩策略，在边缘设备上实现快速处理
- 在MVTec AD上实现80%端到端推理时间降低，性能损失小
- 适合资源受限的工业物联网场景部署
视觉异常检测（VAD）在工业环境中至关重要，需最大限度降低运营成本。在物联网（IoT）环境下部署深度学习模型面临边缘设备计算能力与带宽有限的挑战。本研究通过紧凑高效的处理策略，探索在该约束下实现有效VAD的方法。我们评估了多种数据压缩技术，分析系统延迟与检测准确率之间的权衡。在MVTec AD基准测试中，显著压缩数据可保持接近无压缩数据的异常检测性能。当前结果表明，包括边缘处理、传输和服务器计算在内的端到端推理时间最多减少80%。
原文摘要 · Abstract (English)
Visual Anomaly Detection (VAD) is a key task in industrial settings, where minimizing operational costs is essential. Deploying deep learning models within Internet of Things (IoT) environments introduces specific challenges due to limited computational power and bandwidth of edge devices. This study investigates how to perform VAD effectively under such constraints by leveraging compact, efficient processing strategies. We evaluate several data compression techniques, examining the tradeoff between system latency and detection accuracy. Experiments on the MVTec AD benchmark demonstrate that significant compression can be achieved with minimal loss in anomaly detection performance compared to uncompressed data. Current results show up to 80% reduction in end-to-end inference time, including edge processing, transmission, and server computation.
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。