SAEC让工业视觉检测在资源受限下实现高精度，靠的是智能分配算力。
SAEC: Scene-Aware Enhanced Edge-Cloud Collaborative Industrial Vision Inspection with Multimodal LLM
- 根据场景复杂度动态调度边缘与云端算力，智能分配计算资源。
- 在MVTec AD和KSDD2数据集上准确率达85.11%和82.72%，显著优于基线模型。
- 适合需要低延迟、低功耗的工业缺陷检测场景，尤其适用于资源受限设备。
工业视觉检测需在严苛资源约束下保持高精度，但现有方法存在根本性权衡。多模态大模型（MLLM）虽具备强大推理能力，但计算开销巨大；轻量级边缘模型在复杂案例中表现不足。本文提出SAEC，一种基于MLLM的场景感知增强型边缘-云协同工业视觉检测框架。该框架包含三个协同组件：(1) 面向复杂缺陷检测的高效MLLM微调，(2) 轻量级多尺度场景复杂度估计，(3) 自适应边缘-云调度器。三者协同实现缺陷检测的鲁棒性，通过将多模态推理适配至场景复杂度，并动态平衡边缘与云端计算负载。在MVTec AD和KSDD2数据集上的实验表明，SAEC分别达到85.11%和82.72%的准确率，较Qwen提升22.1%和20.8%，较LLaVA提升33.3%和31.6%。同时，运行时降低最多22.4%，单次正确决策能耗减少40%-74%。代码已开源：https://github.com/YuHao-Tian/SAEC。
原文摘要 · Abstract (English)
Industrial vision inspection requires high accuracy under stringent resource constraints, yet existing approaches face a fundamental trade-off. Multimodal LLMs (MLLMs) deliver strong reasoning capabilities but incur prohibitive computational costs, while lightweight edge models often fail on complex cases. In this paper, we present SAEC, a scene-aware enhanced edge-cloud collaborative industrial vision inspection framework with MLLM. The framework is composed of three synergistic components: (1) Efficient MLLM Fine-Tuning for Complex Defect Inspection, (2) Lightweight Multiscale Scene-Complexity Estimation, and (3) Adaptive Edge-Cloud Scheduler. Together, these modules enable robust defect detection by tailoring multimodal reasoning to scene complexity and dynamically balancing computation between edge and cloud resources. Experimental results on MVTec AD and KSDD2 datasets demonstrate that SAEC attains 85.11% and 82.72% accuracy, surpassing Qwen by 22.1% and 20.8%, and LLaVA by 33.3% and 31.6%. It also reduces runtime by up to 22.4% and cuts energy per correct decision by 40%-74%. The code is available at https://github.com/YuHao-Tian/SAEC.
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。