发表机构
Aalborg University; Pioneer Centre for Artificial Intelligence（奥尔堡大学; 先锋人工智能中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出利用嵌入空间几何结构预测异常检测性能，通过推导AUC下界并引入伪异常探针，在DCASE基准上实现了无异常模型选择，优于传统开发集选择。
AI 中文摘要
异常检测系统通常仅使用正常数据进行训练，而模型选择和评估通常需要带有标签的异常数据。我们研究是否可以在不访问异常数据的情况下预测异常检测性能。对于基于kNN的检测器，我们推导了ROC曲线下面积（AUC）的下界，该下界将检测性能与内点和离群点得分之间的分离度以及它们各自的方差联系起来。在局部缩放模型下，我们利用该界来刻画密度变化、内在维度异质性和跨域不匹配对得分变异性的贡献。随后，我们研究了无异常模型选择，并表明仅凭内点得分方差并不能可靠地预测不同表示下的性能。为解决这一局限性，我们引入了简单的伪异常探针，为估计相对得分分离度提供参考。在DCASE 2022-2025基准上的实验，涵盖四种嵌入模型和208个候选系统，表明基于伪异常的估计器显著改善了无异常模型选择。特别是，多样化的伪异常使得无异常模型选择在域偏移下优于传统的开发集选择。这些结果表明，嵌入空间的几何结构包含关于异常检测性能的预测信息，同时也凸显了仅依赖内点性能估计的表示依赖性。
英文摘要
Anomaly detection systems are often trained using normal data alone, while model selection and evaluation typically require labeled anomalies. We study whether anomaly detection performance can be predicted without access to anomalous data. For kNN-based detectors, we derive a lower bound on the area under the ROC curve (AUC) that relates detection performance to the separation between inlier and outlier scores and to their respective variances. Under a local scaling model, we use this bound to characterize how density variation, intrinsic-dimensional heterogeneity, and cross-domain mismatch contribute to score variability. We then investigate anomaly-free model selection and show that inlier score variance alone does not reliably predict performance across different representations. To address this limitation, we introduce simple pseudo-anomaly probes that provide a reference for estimating relative score separation. Experiments on the DCASE 2022-2025 benchmarks, spanning four embedding models and 208 candidate systems, show that pseudo-anomaly-based estimators substantially improve anomaly-free model selection. In particular, diverse pseudo-anomalies enable anomaly-free model selection to outperform conventional development-set selection under domain shift. These results show that embedding-space geometry contains predictive information about anomaly detection performance while also highlighting the representation-dependent nature of inlier-only performance estimates.
