用互筛机制提升零样本异常检测的精度，不需训练即可用。
Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detection
- 同一批次图像互为参考，用文本过滤噪声特征。
- 在MVTec-AD上分割性能比当前最佳高4.6%和5.7%。
- 适合工业场景中的无训练异常检测任务。
随着视觉语言模型（如CLIP）在零样本和少样本设置中的发展，其被广泛应用于零样本异常检测（ZSAD），其中罕见类别在众多应用中至关重要。本文提出无需训练的FiSeCLIP方法，结合特征匹配与跨模态对齐。由于全数据集测试不切实际，而基于批次的测试更贴近真实工业需求，因此FiSeCLIP利用同一批次内其他图像作为当前图像的参考信息。然而，这些参考图像缺乏标签，可能引入模糊性，故本文采用文本信息来滤除噪声特征。此外，进一步挖掘CLIP内在的局部语义关联能力，适配细粒度异常检测任务，实现更精准的过滤。该方法在多个异常检测基准上表现优异，尤其在MVTec-AD上，分割指标AU-ROC与F_1-max分别优于当前最优方法AdaCLIP 4.6%和5.7%。
原文摘要 · Abstract (English)
With the advent of vision-language models (e.g., CLIP) in zero- and few-shot settings, CLIP has been widely applied to zero-shot anomaly detection (ZSAD) in recent research, where the rare classes are essential and expected in many applications. This study introduces \textbf{FiSeCLIP} for ZSAD with training-free \textbf{CLIP}, combining the feature matching with the cross-modal alignment. Testing with the entire dataset is impractical, while batch-based testing better aligns with real industrial needs, and images within a batch can serve as mutual reference points. Accordingly, FiSeCLIP utilizes other images in the same batch as reference information for the current image. However, the lack of labels for these references can introduce ambiguity, we apply text information to \textbf{fi}lter out noisy features. In addition, we further explore CLIP's inherent potential to restore its local \textbf{se}mantic correlation, adapting it for fine-grained anomaly detection tasks to enable a more accurate filtering process. Our approach exhibits superior performance for both anomaly classification and segmentation on anomaly detection benchmarks, building a stronger baseline for the direction, e.g., on MVTec-AD, FiSeCLIP outperforms the SOTA AdaCLIP by +4.6\%$\uparrow$/+5.7\%$\uparrow$ in segmentation metrics AU-ROC/$F_1$-max.
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。