FreqAnchorAD：基于频率偏差锚定的无语言零样本异常检测
FreqAnchorAD: Language-Free Zero-Shot Anomaly Detection via Frequency-Deviation Anchoring
AI总结：
该研究针对现有零样本异常检测方法未建模频率特征的问题，提出FreqAnchorAD框架，通过LFCM、FDAP和AAS模块在13个工业及医学基准上实现了图像级和像素级异常检测的最优平均性能。
AI中文摘要：
零样本异常检测（ZSAD）旨在无需目标域训练数据的情况下，检测未见目标域中的异常并定位缺陷区域。近期的ZSAD方法基于预训练视觉模型（尤其是CLIP）构建，通过文本提示或可学习视觉表示构建正常与异常参考。这些方法主要在空间特征空间中进行异常判别，而纹理、边界和局部结构的细微变化可能会与正常外观变化混淆。尽管此类缺陷在空间上不明显，但会破坏局部纹理规律性或边界连续性，进而导致不同频带的响应偏差。然而，现有ZSAD方法并未明确建模这些依赖频率的特征。我们的图像域分析表明，局部缺陷在低、中、高频带上均表现出相对于正常参考的空间-频率偏差，这表明异常证据并非普遍由高频响应主导。基于这一观察，我们提出FreqAnchorAD，这是一个频率感知框架，用于组织频率增强的响应以进行锚定相关的异常判别。具体而言，局部频率补偿模块（LFCM）利用局部空间-频率线索增强中间补丁标记；核心判别模块频率偏差锚定投影器（FDAP）沿源导出的通道坐标组织增强后的响应，并通过与正常和异常锚点的相对相似性来测量异常证据；最后，非对称锚定监督（AAS）在稳定正常锚点对齐的同时保留多样的异常模式。在13个工业和医学基准上的实验表明，FreqAnchorAD在图像级异常识别和像素级缺陷定位中实现了最先进的平均性能。
英文摘要：
Zero-shot anomaly detection (ZSAD) aims to detect anomalies and localize defective regions in unseen target domains without target training data. Recent ZSAD methods build on pretrained vision models, particularly CLIP, and construct normal and anomaly references from textual prompts or learnable visual representations. These methods perform anomaly discrimination primarily in spatial feature spaces, where subtle changes in texture, boundaries, and local structures can be confused with normal appearance variations. Although inconspicuous spatially, such defects can disrupt local texture regularity or boundary continuity, inducing response deviations across frequency bands. However, existing ZSAD methods do not explicitly model these frequency-dependent characteristics. Our image-domain analysis reveals that local defects exhibit spatial-frequency deviations from normal references across low-, middle-, and high-frequency bands, indicating that anomaly evidence is not universally dominated by high-frequency responses. Motivated by this observation, we propose FreqAnchorAD, a frequency-aware framework that organizes frequency-enhanced responses for anchor-relative anomaly discrimination. Specifically, the Local Frequency Compensation Module (LFCM) enhances intermediate patch tokens with local spatial-frequency cues. The Frequency-Deviation Anchor Projector (FDAP), our core discrimination module, organizes enhanced responses along a source-derived channel coordinate and measures anomaly evidence through relative similarity to normal and anomaly anchors. Finally, Asymmetric Anchor Supervision (AAS) stabilizes normal-anchor alignment while preserving diverse anomaly patterns. Experiments on thirteen industrial and medical benchmarks show that FreqAnchorAD achieves state-of-the-art mean performance in image-level anomaly recognition and pixel-level defect localization.
