Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution Detection
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.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningOut-of-Distribution DetectionOut of Distribution (OOD) DetectionUncertainty QuantificationSimilar Papers 제목 키워드 기반
Humble your Overconfident Networks: Unlearning Overfitting via Sequential Monte Carlo Tempered Deep Ensembles
Sequential Monte Carlo (SMC) methods offer a principled approach to Bayesian uncertainty quantification but are traditionally limited by the need for full-batch gradient evaluations. We introduce a scalable variant by in…
image-classificationImage ClassificationOut of Distribution (OOD) DetectionTransfer Learning+1Batch Ensemble for Variance Dependent Regret in Stochastic Bandits
Efficiently trading off exploration and exploitation is one of the key challenges in online Reinforcement Learning (RL). Most works achieve this by carefully estimating the model uncertainty and following the so-called o…
Multi-Armed BanditsReinforcement Learning (RL)Is BatchEnsemble a Single Model? On Calibration and Diversity of Efficient Ensembles
In resource-constrained and low-latency settings, uncertainty estimates must be efficiently obtained. Deep Ensembles provide robust epistemic uncertainty (EU) but require training multiple full-size models. BatchEnsemble…
Learn what you can't learn: Regularized Ensembles for Transductive out-of-distribution detection
Machine learning models are often used in practice once they achieve good generalization results on in-distribution (ID) holdout data. To predict test sets in the wild, they should detect samples they cannot predict well…
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionTASAC: a twin-actor reinforcement learning framework with stochastic policy for batch process control
Due to their complex nonlinear dynamics and batch-to-batch variability, batch processes pose a challenge for process control. Due to the absence of accurate models and resulting plant-model mismatch, these problems becom…
Reinforcement Learning (RL)