少样本异常检测阈值认证极限研究

1. 12:00
   arXiv · Machine Learning Theory

   少样本异常检测中，分布无关的阈值认证需要多少类别样本？——DINOv2 PCA 残差排序器的可行性边界与 CRESS 协议

   研究用冻结 DINOv2 PCA 残差排序器在 15 个 MVTec 和 12 个 VisA 类别上验证少样本异常阈值：目标仅留一图（LOIO）校准在 α=0.20 时经验 FAR 达 0.341，为名义水平的 1.7 倍。

Current heat 9·Comparable peak 10（Oct 2）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.