SAEC：基于多模态大语言模型的场景感知增强型边云协同工业视觉检测
SAEC: Scene-Aware Enhanced Edge-Cloud Collaborative Industrial Vision Inspection with Multimodal LLM
AI总结：
SAEC框架通过高效MLLM微调、轻量级场景复杂度估计与自适应边云调度，在工业视觉检测中实现精度与资源效率的协同优化，在MVTec AD和KSDD2上准确率分别达85.11%和82.72%，显著超越Qwen和LLaVA，并降低运行时间与能耗。
摘要：
工业视觉检测要求在严格资源约束下实现高精度，但现有方法面临根本性权衡。多模态大语言模型（MLLMs）具备强大的推理能力，却带来难以承受的计算成本，而轻量级边缘模型在复杂场景下往往失效。本文提出SAEC，一个基于MLLM的场景感知增强型边云协同工业视觉检测框架。该框架由三个协同组件构成：（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）自适应边云调度器。这些模块共同通过将多模态推理适配于场景复杂度，并在边缘与云资源之间动态平衡计算，实现鲁棒的缺陷检测。在MVTec AD和KSDD2数据集上的实验结果表明，SAEC分别达到85.11%和82.72%的准确率，比Qwen高出22.1%和20.8%，比LLaVA高出33.3%和31.6%。同时，运行时间最多降低22.4%，每次正确决策的能耗降低40%-74%。代码已开源：https://github.com/YuHao-Tian/SAEC。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
