基于指称的工业异常分割
Referring Industrial Anomaly Segmentation
AI总结：
基于指称的工业异常分割通过语言引导检测，利用双查询标记与掩码分组变压器提升多尺度分割效果，实现开放集异常检测能力。
摘要：
工业异常检测（IAD）对制造至关重要，但传统方法面临显著挑战：无监督方法产生粗糙的局部化结果需要手动阈值，而有监督方法由于数据稀缺且不平衡而过拟合。两者都受到“一异常类别，一模型”的限制。为了解决这个问题，我们提出了基于指称的工业异常分割（RIAS），一种利用语言引导检测的范式。RIAS从文本描述中生成精确的掩码，无需手动阈值，并使用通用提示检测多种异常，仅需一个模型。我们引入了MVTec-Ref数据集来支持这一工作，该数据集具有多样的指称表达，并专注于异常模式，特别是包含95%的小异常。我们还提出了双查询标记与掩码分组变压器（DQFormer）基准，通过语言门控多级聚合（LMA）改进多尺度分割。与传统方法使用冗余查询不同，DQFormer仅使用“异常”和“背景”标记进行高效的视觉-文本整合。实验表明，RIAS在推动IAD向开放集能力发展方面具有有效性。代码：https://github.com/swagger-coder/RIAS-MVTec-Ref。
英文摘要：
Industrial Anomaly Detection (IAD) is vital for manufacturing, yet traditional methods face significant challenges: unsupervised approaches yield rough localizations requiring manual thresholds, while supervised methods overfit due to scarce, imbalanced data. Both suffer from the "One Anomaly Class, One Model" limitation. To address this, we propose Referring Industrial Anomaly Segmentation (RIAS), a paradigm leveraging language to guide detection. RIAS generates precise masks from text descriptions without manual thresholds and uses universal prompts to detect diverse anomalies with a single model. We introduce the MVTec-Ref dataset to support this, designed with diverse referring expressions and focusing on anomaly patterns, notably with 95% small anomalies. We also propose the Dual Query Token with Mask Group Transformer (DQFormer) benchmark, enhanced by Language-Gated Multi-Level Aggregation (LMA) to improve multi-scale segmentation. Unlike traditional methods using redundant queries, DQFormer employs only "Anomaly" and "Background" tokens for efficient visual-textual integration. Experiments demonstrate RIAS's effectiveness in advancing IAD toward open-set capabilities. Code: https://github.com/swagger-coder/RIAS-MVTec-Ref.
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。
