Out-of-distribution (OOD) detection has recently received much attention from the machine learning community due to its importance in deploying machine learning models in real-world applications. In this paper we propose an uncertainty quantification approach by modelling the distribution of features. We further incorporate an efficient ensemble mechanism, namely batch-ensemble, to construct the batch-ensemble stochastic neural networks (BE-SNNs) and overcome the feature collapse problem. We compare the performance of the proposed BE-SNNs with the other state-of-the-art approaches and show that BE-SNNs yield superior performance on several OOD benchmarks, such as the Two-Moons dataset, the FashionMNIST vs MNIST dataset, FashionMNIST vs NotMNIST dataset, and the CIFAR10 vs SVHN dataset.
翻译:由于机器学习界在实际应用中采用机器学习模型的重要性,机器学习界最近非常关注外向探测,因为机器学习界在实际应用中的重要性。在本文件中,我们提出通过对地貌分布进行建模的不确定性量化方法。我们进一步纳入了一个高效的混合机制,即批量组合机制,以构建批量组合式透视神经网络(BE-SNN)并克服特征崩溃问题。我们比较了拟议的BE-SNN的性能与其他最先进的方法,并表明BE-SNN的性能优于若干OOD基准,例如双制卫星数据集、时装MNISIP对MIS数据集、时装MISIS对非MNIST数据集和CIFAR10对SVHN数据集。