让AI看懂工业图像中哪条逻辑规则被违反，还能说出证据。
Interpretable Logical Anomaly Classification via Constraint Decomposition and Instruction Fine-Tuning
- 把复杂逻辑规则拆成可验证的小问题，逐步推理
- 在真实工业数据上准确识别违规类型，支持解释性输出
- 适合需要透明质检的制造业场景
逻辑异常是工业图像中对象数量、空间布局和组合关系违反预设约束的现象。以往方法多将异常检测视为二分类任务，无法指明具体违反哪条规则，对质量保障帮助有限。本文提出逻辑异常分类（LAC）任务，实现异常检测与细粒度违规分类的一体化推理。为此，我们设计了LogiCls框架，将复杂逻辑约束分解为一系列可验证的子查询，并构建以数据为中心的指令生成流程，通过链式思维（CoT）监督信号、精准定位标注和多样图文增强，使视觉语言模型具备逻辑敏感推理能力。训练采用难度感知重采样策略，强化难例和长尾约束类型的学习。大量实验表明，LogiCls能实现稳健、可解释且高精度的工业逻辑异常分类，不仅能预测违规类别，还可提供完整的证据链。
原文摘要 · Abstract (English)
Logical anomalies are violations of predefined constraints on object quantity, spatial layout, and compositional relationships in industrial images. While prior work largely treats anomaly detection as a binary decision, such formulations cannot indicate which logical rule is broken and therefore offer limited value for quality assurance. We introduce Logical Anomaly Classification (LAC), a task that unifies anomaly detection and fine-grained violation classification in a single inference step. To tackle LAC, we propose LogiCls, a vision-language framework that decomposes complex logical constraints into a sequence of verifiable subqueries. We further present a data-centric instruction synthesis pipeline that generates chain-of-thought (CoT) supervision for these subqueries, coupling precise grounding annotations with diverse image-text augmentations to adapt vision language models (VLMs) to logic-sensitive reasoning. Training is stabilized by a difficulty-aware resampling strategy that emphasizes challenging subqueries and long tail constraint types. Extensive experiments demonstrate that LogiCls delivers robust, interpretable, and accurate industrial logical anomaly classification, providing both the predicted violation categories and their evidence trails.
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。