AnoStyler：通过轻量级风格迁移实现文本驱动的局部异常生成
AnoStyler: Text-Driven Localized Anomaly Generation via Lightweight Style Transfer
AI总结：
AnoStyler将零样本异常生成建模为文本引导的风格迁移，利用类别无关流程生成异常掩码和文本提示，并通过基于CLIP损失训练的轻量级U-Net生成视觉逼真且语义对齐的局部异常图像，在MVTec-AD和VisA上优于现有方法并提升异常检测性能。
摘要：
异常生成已被广泛探索，以解决现实数据中异常图像稀缺的问题。然而，现有方法通常至少存在以下一个限制，阻碍了其实际部署：（1）生成的异常缺乏视觉真实感；（2）依赖大量真实图像；（3）使用内存密集型的重型模型架构。为克服这些限制，我们提出AnoStyler，一种轻量且有效的方法，将零样本异常生成构建为文本引导的风格迁移。给定一张正常图像及其类别标签和预期的缺陷类型，使用可泛化的类别无关流程生成指示局部异常区域的异常掩码以及表示正常和异常状态的两类文本提示。一个使用基于CLIP的损失函数训练的轻量级U-Net模型被用于将正常图像风格化为视觉逼真的异常图像，其中异常由异常掩码定位，并与文本提示在语义上对齐。在MVTec-AD和VisA数据集上的大量实验表明，AnoStyler在生成高质量和多样化的异常图像方面优于现有异常生成方法。此外，使用这些生成的异常有助于提升异常检测性能。
英文摘要：
Anomaly generation has been widely explored to address the scarcity of anomaly images in real-world data. However, existing methods typically suffer from at least one of the following limitations, hindering their practical deployment: (1) lack of visual realism in generated anomalies; (2) dependence on large amounts of real images; and (3) use of memory-intensive, heavyweight model architectures. To overcome these limitations, we propose AnoStyler, a lightweight yet effective method that frames zero-shot anomaly generation as text-guided style transfer. Given a single normal image along with its category label and expected defect type, an anomaly mask indicating the localized anomaly regions and two-class text prompts representing the normal and anomaly states are generated using generalizable category-agnostic procedures. A lightweight U-Net model trained with CLIP-based loss functions is used to stylize the normal image into a visually realistic anomaly image, where anomalies are localized by the anomaly mask and semantically aligned with the text prompts. Extensive experiments on the MVTec-AD and VisA datasets show that AnoStyler outperforms existing anomaly generation methods in generating high-quality and diverse anomaly images. Furthermore, using these generated anomalies helps enhance anomaly detection performance.
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。
