用结构特征提升异常检测精度，超越传统最大池化方法。
StructCore: Structure-Aware Image-Level Scoring for Training-Free Unsupervised Anomaly Detection
- 通过低维结构描述符捕捉异常分布与空间特征
- 在MVTec AD上达99.6%图像级AUROC，VisA上98.4%
- 无需训练，可直接用于现有模型的异常评分
在基于记忆库的无监督异常检测中，最大池化是将异常分数图转换为图像级决策的通用方法。然而，它仅依赖单一极端响应，忽略了异常证据在图像中的分布与结构信息，常导致正常与异常分数重叠。本文提出StructCore，一种无需训练、感知结构的图像级评分方法。给定异常分数图，StructCore计算一个低维结构描述符φ(S)，捕捉分布与空间特性，并通过从正常样本中估计的对角马氏距离进行校准，实现图像级评分，不改变像素级定位。在MVTec AD和VisA数据集上，图像级AUROC分别达到99.6%和98.4%，证明了利用最大池化遗漏的结构信号可显著提升异常检测性能。
原文摘要 · Abstract (English)
Max pooling is the de facto standard for converting anomaly score maps into image-level decisions in memory-bank-based unsupervised anomaly detection (UAD). However, because it relies on a single extreme response, it discards most information about how anomaly evidence is distributed and structured across the image, often causing normal and anomalous scores to overlap. We propose StructCore, a training-free, structure-aware image-level scoring method that goes beyond max pooling. Given an anomaly score map, StructCore computes a low-dimensional structural descriptor phi(S) that captures distributional and spatial characteristics, and refines image-level scoring via a diagonal Mahalanobis calibration estimated from train-good samples, without modifying pixel-level localization. StructCore achieves image-level AUROC scores of 99.6% on MVTec AD and 98.4% on VisA, demonstrating robust image-level anomaly detection by exploiting structural signatures missed by max pooling.
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。