AI 中文总结
研究异常检测不平衡时评估指标，分析AUROC、AUPR、F1分数和MCC四个常见指标在不同不平衡水平下的行为，通过指标景观研究提供直观视图，为跨不同不平衡比率数据集解释和比较异常检测结果提供实用指导。
AI 中文摘要
异常检测本质上具有严重的类别不平衡特征，这使得评估指标的解释具有挑战性。尽管AUROC、AUPR、F1分数和MCC等指标被广泛使用，但它们的值根据异常比率传达不同的含义。在这项工作中，我们分析了这四个常见异常检测指标在不同不平衡水平下的行为。我们专注于指标景观的研究，即将指标值与真阳性率和真阴性率相关联的可视化，提供了指标偏好和稳定性的直观视图。我们的分析为解释和比较不同不平衡比率数据集的异常检测结果提供了实用指导。
英文摘要
Anomaly detection is inherently characterised by severe class imbalance, making the interpretation of evaluation metrics challenging. Although metrics such as AUROC, AUPR, F1-score, and MCC are widely used, their values convey different meanings depending on the anomaly ratio. In this work, we analyse the behaviour of those four common anomaly detection metrics under varying levels of imbalance. We focus on the study of metric landscapes, visualisations that relate metric values to true positive and true negative rates, providing an intuitive view of metric preferences and stability. Our analysis offers practical guidance for interpreting and comparing anomaly detection results across datasets with different imbalance ratios.
CommentsPublished in EUVIP 2026
