Detecting out-of-distribution (OOD) data at inference time is crucial for
many applications of machine learning. We present XOOD: a novel extreme
value-based OOD detection framework for image classification that consists of
two algorithms. The first, XOOD-M, is completely unsupervised, while the second
XOOD-L is self-supervised. Both algorithms rely on the signals captured by the
extreme values of the data in the activation layers of the neural network in
order to distinguish between in-distribution and OOD instances. We show
experimentally that both XOOD-M and XOOD-L outperform state-of-the-art OOD
detection methods on many benchmark data sets in both efficiency and accuracy,
reducing false-positive rate (FPR95) by 50%, while improving the inferencing
time by an order of magnitude.

本研究提出了一种基于极值的新型 OOD 检测框架 XOOD，包括两个算法：完全无监督的 XOOD-M 和自我监督的 XOOD-L，两者都依赖于神经网络中激活层数据的极值信号以区分内部分布和 OOD 实例。实验证明，XOOD-M 和 XOOD-L 在效率和准确性方面均优于现有的状态 - of-the-art OOD 检测方法，在降低误报率（FPR95）50％，同时将推理时间提高一个数量级。