AnomalyAgent: 用于零样本/少样本异常检测的无训练智能体模型
AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection
AI总结：
提出一种基于多模态大语言模型的无训练智能体框架AnomalyAgent，通过定制工具集和记忆模块实现零样本/少样本异常检测，在逻辑/上下文异常等复杂场景中优于现有方法。
摘要：
受益于视觉语言模型（如CLIP）的泛化能力，许多零样本/少样本异常检测方法已在各种数据集上取得了令人印象深刻的检测性能。然而，它们需要在大规模辅助数据集上进行大量训练以适应异常检测，并且其推理主要依赖于基于视觉-文本嵌入相似度的异常分数，缺乏检测需要深度上下文理解的复杂异常的推理能力。为了解决这一局限性，我们提出了 extbf{AnomalyAgent}，一种新颖的无训练智能体框架，利用多模态大语言模型的先进推理和泛化能力进行异常检测。关键要素包括： extbf{1)}一个全面的以异常为中心的工具集，能够在零样本设置下实现自适应MLLM驱动的智能体异常推理； extbf{2)}一个定制的记忆模块，通过少样本上下文参考示例来支撑异常推理。我们将评估从广泛使用的基准测试中检测简单异常（例如，裂纹和凹痕等表面缺陷以及明显病变）扩展到更多样化的异常类型，例如物流和制造环境中的逻辑/上下文异常。大量实验结果表明，我们的AnomalyAgent与无训练的基于VLM的异常检测和通用智能体方法相比，实现了显著更好的性能，突显了其在零样本和少样本异常检测设置中的优越泛化能力。代码实现可在此地址找到。
英文摘要：
Benefiting from generalizability of vision-language models (VLMs) such as CLIP, many zero-/few-shot anomaly detection (AD) approaches have achieved impressive detection performance across various datasets. Nevertheless, they require substantial training on large auxiliary datasets to adapt VLMs to anomaly detection, and their inference largely relies on visual-text embedding similarity-based anomaly scores, lacking reasoning abilities to detect complex anomalies that require in-depth contextual understanding. To address this limitation, we propose \textbf{AnomalyAgent}, a novel training-free, agentic framework that leverages the advanced reasoning and generalization capabilities of multimodal large language models (MLLMs) for anomaly detection. The key ingredients include \textbf{1)} a comprehensive anomaly-centric toolset that enables adaptive MLLM-driven, agentic anomaly reasoning in zero-shot settings, and \textbf{2)} a customized memory module that grounds anomaly reasoning with few-shot, in-context reference examples. We extend evaluation beyond the detection of simple anomalies (e.g., surface defects like cracks and dents and clear lesions) in widely used benchmarks to more diverse types of anomalies such as logical/contextual anomalies in logistics and manufacturing settings. Extensive experiment results demonstrate that our AnomalyAgent achieves substantially better performance compared to training-free VLM-based AD and generic agentic methods, highlighting its superior generalization capability in both zero-shot and few-shot anomaly detection settings. The code implementation can be find at this address.
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。
