ProtoAnomalyNCD：面向工业场景多类别新颖异常发现的原型学习方法
ProtoAnomalyNCD: Prototype Learning for Multi-class Novel Anomaly Discovery in Industrial Scenarios
AI总结：
针对工业场景多类新颖异常发现需求，提出基于原型学习的ProtoAnomalyNCD框架，结合Grounded SAM先验定位与异常图引导注意力模块，在多个工业数据集上性能超越现有最优方法。
摘要：
现有工业异常检测方法主要判断是否存在异常，但实际应用还需要发现并分类多种异常类型。由于工业异常语义特征细微，且现有方法未充分利用图像先验，直接聚类方法往往表现不佳。为解决这些挑战，我们提出ProtoAnomalyNCD，这是一个基于原型学习的框架，用于发现多类未见异常类别，可与多种异常检测方法集成。首先，为抑制背景杂波，我们利用带文本提示的Grounded SAM定位目标区域，作为异常分类网络的先验。其次，由于异常通常表现为产品上细微的细粒度模式，我们引入异常图引导注意力模块，在该模块中设计了区域引导因子，帮助注意力模块区分背景、目标区域和异常区域。通过将定位的产品区域和异常图同时作为先验，该模块增强异常特征，同时抑制背景噪声并保留正常特征用于对比学习。最后，在统一的原型学习框架下，ProtoAnomalyNCD对未见异常类别进行发现和聚类，同时实现多类型异常分类。我们进一步将方法扩展至检测未见离群点，实现任务级统一。我们的方法在MVTec AD、MTD和Real-IAD数据集上性能优于当前最优方法。
英文摘要：
Existing industrial anomaly detection methods mainly determine whether an anomaly is present. However, real-world applications also require discovering and classifying multiple anomaly types. Since industrial anomalies are semantically subtle and current methods do not sufficiently exploit image priors, direct clustering approaches often perform poorly. To address these challenges, we propose ProtoAnomalyNCD, a prototype-learning-based framework for discovering unseen anomaly classes of multiple types that can be integrated with various anomaly detection methods. First, to suppress background clutter, we leverage Grounded SAM with text prompts to localize object regions as priors for the anomaly classification network. Next, because anomalies usually appear as subtle and fine-grained patterns on the product, we introduce an Anomaly-Map-Guided Attention block. Within this block, we design a Region Guidance Factor that helps the attention module distinguish among background, object regions, and anomalous regions. By using both localized product regions and anomaly maps as priors, the module enhances anomalous features while suppressing background noise and preserving normal features for contrastive learning. Finally, under a unified prototype-learning framework, ProtoAnomalyNCD discovers and clusters unseen anomaly classes while simultaneously enabling multi-type anomaly classification. We further extend our method to detect unseen outliers, achieving task-level unification. Our method outperforms state-of-the-art approaches on the MVTec AD, MTD, and Real-IAD datasets.
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。
