论文标题
Xood：基于极值的图像分类检测
XOOD: Extreme Value Based Out-Of-Distribution Detection For Image Classification
论文作者
论文摘要
在推理时间检测到分布（OOD）数据对于机器学习的许多应用至关重要。我们提出Xood：一种用于图像分类的新型基于极值的OOD检测框架，由两种算法组成。第一个是Xood-M完全无监督，而第二个Xood-L则是自欺欺人的。两种算法都依赖于神经网络激活层中数据的极端值捕获的信号，以区分分布和OOD实例。我们通过实验表明，Xood-M和Xood-L均优于效率和准确性的许多基准数据集的最先进的OOD检测方法，从而将假阳性率（FPR95）降低了50％，同时将推论时间提高了数量级。
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.
