Anomaly detection (AD) plays a crucial role in many safety-critical application domains. The challenge of adapting an anomaly detector to drift in the normal data distribution, especially when no training data is available for the "new normal," has led to the development of zero-shot AD techniques. In this paper, we propose a simple yet effective method called Adaptive Centered Representations (ACR) for zero-shot batch-level AD. Our approach trains off-the-shelf deep anomaly detectors (such as deep SVDD) to adapt to a set of inter-related training data distributions in combination with batch normalization, enabling automatic zero-shot generalization for unseen AD tasks. This simple recipe, batch normalization plus meta-training, is a highly effective and versatile tool. Our theoretical results guarantee the zero-shot generalization for unseen AD tasks; our empirical results demonstrate the first zero-shot AD results for tabular data and outperform existing methods in zero-shot anomaly detection and segmentation on image data from specialized domains. Code is at https://github.com/aodongli/zero-shot-ad-via-batch-norm

翻译：异常检测（AD）在众多安全关键应用领域中扮演着重要角色。由于异常检测器需要适应常规数据分布的变化，尤其是在缺乏"新常态"训练数据的情况下，这一挑战催生了零样本异常检测技术的发展。本文提出一种简洁高效的名为自适应中心化表示（ACR）的方法，用于零样本批量级异常检测。该方法通过结合批量归一化技术，训练现成的深度异常检测器（如深度支持向量数据描述），使其适应一组相互关联的训练数据分布，从而实现对未见异常检测任务的自动零样本泛化。这种"批量归一化+元训练"的简单配方是一种高效且通用的工具。理论分析保证了该方法在未见异常检测任务上的零样本泛化能力；实验结果表明，该方法首次实现表格数据的零样本异常检测，并在专业领域图像数据的零样本异常检测与分割任务中优于现有方法。代码已开源：https://github.com/aodongli/zero-shot-ad-via-batch-norm