用视觉语言模型生成问题，自动检测工业图像中隐性逻辑异常并给出解释。
LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions
- 通过自动生成问题构建检查清单，识别违反逻辑约束的异常。
- 在MVTec LOCO数据集上达到87.6% AUROC和87.0% F1-max的顶尖性能。
- 无需训练和标注，适用于工业场景，适合需要可解释性的质检应用。
异常检测（AD）旨在识别偏离标准模式的样本，是过程控制中的关键工具。逻辑异常可能在视觉上正常，却违反物体存在、排列或数量等预设约束，需依赖推理与可解释性。我们提出LogicQA框架，通过生成视觉语言模型的问题形成检查清单，并收集回答以识别逻辑约束违规。该方法无需训练与标注，可在少样本条件下运行。在公开基准MVTec LOCO AD上，取得87.6% AUROC与87.0% F1-max的领先性能，并提供异常解释。同时，在半导体SEM企业数据上表现优异，验证其在工业应用中的有效性。
原文摘要 · Abstract (English)
Anomaly Detection (AD) focuses on detecting samples that differ from the standard pattern, making it a vital tool in process control. Logical anomalies may appear visually normal yet violate predefined constraints on object presence, arrangement, or quantity, depending on reasoning and explainability. We introduce LogicQA, a framework that enhances AD by providing industrial operators with explanations for logical anomalies. LogicQA compiles automatically generated questions into a checklist and collects responses to identify violations of logical constraints. LogicQA is training-free, annotation-free, and operates in a few-shot setting. We achieve state-of-the-art (SOTA) Logical AD performance on public benchmarks, MVTec LOCO AD, with an AUROC of 87.6 percent and an F1-max of 87.0 percent along with the explanations of anomalies. Also, our approach has shown outstanding performance on semiconductor SEM corporate data, further validating its effectiveness in industrial applications.
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。