LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions
It addresses the problem of detecting logical anomalies in industrial settings for operators, providing explanations, but it is incremental as it builds on existing anomaly detection methods.
The paper tackles logical anomaly detection by introducing LogicQA, a framework that uses vision-language models to generate questions for identifying violations of logical constraints, achieving state-of-the-art performance with an AUROC of 87.6% and F1-max of 87.0% on the MVTec LOCO AD benchmark.
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.