用文字描述精准定位工业缺陷，一模型通吃各类异常。
Referring Industrial Anomaly Segmentation
- 用文本引导生成精确分割掩码，无需手动调阈值。
- 95%小缺陷数据集上实现高精度分割，支持开放集检测。
- 仅用两个查询词高效融合图文信息，适合工业质检场景。
工业异常检测对制造至关重要，但传统方法面临挑战：无监督方法定位粗糙需人工设定阈值，有监督方法因数据稀少且不平衡易过拟合，且均受限于‘一类异常一模型’。为此，我们提出参照式工业异常分割（RIAS），利用语言指导检测。RIAS通过文本描述生成精确掩码，无需人工阈值，并使用通用提示词，仅用一个模型即可检测多种异常。我们构建了MVTec-Ref数据集，包含多样化的指代表达，聚焦异常模式，其中95%为小尺寸异常。同时提出双查询令牌与掩码组变换器（DQFormer），结合语言门控多级聚合（LMA）提升多尺度分割性能。不同于传统冗余查询设计，DQFormer仅采用‘异常’和‘背景’两个查询词，实现高效视觉-语言融合。实验表明，RIAS有效推动工业异常检测迈向开放集能力。代码已开源。
原文摘要 · Abstract (English)
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.
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。