基于特征匹配与跨模态对齐及互滤波的零样本异常检测
Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detection
AI总结：
本文提出 FiSeCLIP，结合特征匹配与跨模态对齐，利用批次内图像互参考并通过文本滤波噪声特征，在零样本异常检测中实现优于 SOTA 的性能。
摘要：
随着视觉-语言模型（如 CLIP）在零样本和少样本场景下的兴起，CLIP 近期已被广泛应用于零样本异常检测（ZSAD）研究中，其中罕见类别在许多应用中是至关重要且被期望出现的。本研究引入了 FiSeCLIP 用于基于免训练 CLIP 的 ZSAD，将特征匹配与跨模态对齐相结合。使用整个数据集进行测试是不切实际的，而基于批次的测试更符合实际工业需求，且批次内的图像可作为相互参考点。因此，FiSeCLIP 利用同一批次中的其他图像作为当前图像的参考信息。然而，这些参考缺乏标签可能引入歧义，我们应用文本信息来滤除噪声特征。此外，我们进一步探索 CLIP 的内在潜力以恢复其局部语义关联，使其适应细粒度异常检测任务，从而实现更准确的滤波过程。我们的方法在异常检测基准上的异常分类和分割均展现出卓越性能，为该方向构建了更强的基线，例如在 MVTec-AD 上，FiSeCLIP 在分割指标 AU-ROC/F1-max 上比 SOTA AdaCLIP 高出 +4.6%↑/+5.7%↑。
英文摘要：
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.
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。
