面向少样本多类异常检测的双向多模态提示学习与尺度感知训练
Bidirectional Multimodal Prompt Learning with Scale-Aware Training for Few-Shot Multi-Class Anomaly Detection
把文本提示与视觉提示做双向交互、并用全局+局部双视图训练尺度感知前缀，为少样本多类异常检测提供了一种无需异常类型描述、无需外部模块的轻量提示学习范式，可直接迁移到工业质检与医学异常定位。
原文依据 AnoPLe employs bidirectional interactions between textual and visual prompts, allowing class semantics and instance-level cues to refine one another
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论少样本多类异常检测在真实工业场景中至关重要：此时仅有少量正常样本可用，却需要检测众多物体类型。该设定极具挑战性，因为缺陷模式在不同类别间差异很大，而正常样本始终稀缺。现有的基于视觉语言模型的方法通常依赖类别特定的异常描述或辅助模块，限制了可扩展性与计算效率。本文提出 AnoPLe，一个轻量的多模态提示学习框架，它摆脱了对异常类型文本描述的依赖，且不使用任何外部模块。AnoPLe 在文本提示与视觉提示之间建立双向交互，使类别语义与实例级线索相互精炼，形成类别条件化的表征，从而捕捉跨类别共享的正常模式。为增强定位能力，我们设计了一个在全局与局部视图上训练的尺度感知前缀，使提示能够同时捕捉全局上下文与细粒度细节。此外，对齐损失将局部异常证据传播到全局特征，增强了像素级与图像级预测之间的一致性。尽管方法简单，AnoPLe 在少样本多类设定下于 MVTec-AD、VisA 和 Real-IAD 上取得了强劲性能，超越了先前方法，同时保持高效且无需专家手工构造的异常描述。此外，AnoPLe 对未见异常具有良好的泛化能力，并能有效扩展到医学领域。
英文原文摘要 1556 字符
Few-shot multi-class anomaly detection is crucial in real industrial settings, where only a few normal samples are available while numerous object types must be inspected. This setting is challenging as defect patterns vary widely across categories while normal samples remain scarce. Existing vision-language model-based approaches typically depend on class-specific anomaly descriptions or auxiliary modules, limiting both scalability and computational efficiency. In this work, we propose AnoPLe, a lightweight multimodal prompt learning framework that removes reliance on anomaly-type textual descriptions and avoids any external modules. AnoPLe employs bidirectional interactions between textual and visual prompts, allowing class semantics and instance-level cues to refine one another and form class-conditioned representations that capture shared normal patterns across categories. To enhance localization, we design a scale-aware prefix trained on both global and local views, enabling the prompts to capture both global context and fine-grained details. In addition, alignment loss propagates local anomaly evidence to global features, strengthening the consistency between pixel- and image-level predictions. Despite its simplicity, AnoPLe achieves strong performance on MVTec-AD, VisA, and Real-IAD under the few-shot multi-class setting, surpassing prior approaches while remaining efficient and free from expert-crafted anomaly descriptions. Moreover, AnoPLe generalizes well to unseen anomalies and extends effectively to the medical domain.