Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution Detection
This addresses the problem of reliable uncertainty estimation for deploying machine learning models in real-world applications, representing an incremental improvement.
The paper tackles out-of-distribution detection by proposing batch-ensemble stochastic neural networks to model feature distributions and avoid feature collapse, achieving superior performance on benchmarks like Two-Moons and CIFAR10 vs SVHN.
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.