GenAU: 基于语言的工业异常理解与视觉语言模型
GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models
AI总结：
提出GenAU框架，统一图像级检测、像素级分割、多类型异常检测和缺陷分析，通过两个分割标记实现语言引导的定位，在VisA和Real-IAD上取得最优零样本检测性能。
摘要：
工业检测需要的不仅仅是二元异常检测：一个实用的系统应确定是否存在异常、定位缺陷区域、识别缺陷类型并提供可解释的视觉证据。现有的基于CLIP的方法能很好地检测和定位异常，但提供的语言级缺陷理解有限，而经过指令调优的视觉语言模型可以描述缺陷，但本身不产生像素级掩码。我们提出GenAU，一个用于工业异常理解的通用视觉语言框架，它在单个指令遵循模型中统一了图像级检测、像素级分割、多类型异常检测和缺陷分析。GenAU通过两个分割标记[SEG_defect]和[SEG_normal]增强视觉语言模型，其隐藏状态作为语言引导的查询，作用于多尺度视觉特征以实现像素级定位；图像级分数将该图与解码器的文本正常/缺陷决策融合，而语言解码器生成结构化的缺陷感知响应。通过联合语言建模和分割目标训练，GenAU在一个架构和配方中覆盖所有四个任务，以量化的检测和分割代价增加了零样本多类型检测和语言引导的缺陷分析。在跨数据集基准测试中，GenAU在VisA和Real-IAD上取得了基于CLIP的零样本方法中最强的图像级检测，分割性能接近但未超过专门的CLIP基线。
英文摘要：
Industrial inspection requires more than binary anomaly detection: a practical system should determine whether an anomaly exists, localize the defective region, identify the defect type, and provide interpretable visual evidence. Existing CLIP-based methods detect and localize anomalies well but offer limited language-level defect understanding, while instruction-tuned vision-language models can describe defects but do not natively produce pixel-level masks. We introduce GenAU, a Generalist vision-language framework for industrial Anomaly Understanding that unifies image-level detection, pixel-level segmentation, multi-type anomaly detection, and defect analysis in a single instruction-following model. GenAU augments a vision-language model with two segmentation tokens, [SEG_defect] and [SEG_normal], whose hidden states act as language-grounded queries over multi-scale visual features for pixel-level localization; the image-level score fuses this map with the decoder's textual normal/defect decision, while the language decoder produces structured defect-aware responses. Trained with a joint language-modeling and segmentation objective, GenAU covers all four tasks within one architecture and recipe, adding zero-shot multi-type detection and language-grounded defect analysis at a quantified cost to detection and segmentation. Across cross-dataset benchmarks, GenAU attains the strongest image-level detection among CLIP-based zero-shot methods on VisA and Real-IAD, with segmentation approaching but not surpassing specialized CLIP baselines.
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。
