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 aims to deliver ensemble-like EU at far lower parameter and memory cost by applying learned rank-1 perturbations to a shared base network. We show that BatchEnsemble not only underperforms Deep Ensembles but closely tracks a single model baseline in terms of accuracy, calibration and out-of-distribution (OOD) detection on CIFAR10/10C/SVHN. A controlled study on MNIST finds members are near-identical in function and parameter space, indicating limited capacity to realize distinct predictive modes. Thus, BatchEnsemble behaves more like a single model than a true ensemble.

翻译：在资源受限和低延迟场景中，必须高效地获取不确定性估计。深度集成方法能够提供稳健的认知不确定性，但需要训练多个完整规模的模型。BatchEnsemble 旨在通过对共享基础网络施加学习得到的秩-1扰动，以远更低的参数量和内存成本实现类似集成的认知不确定性。我们证明，在 CIFAR10/10C/SVHN 数据集上，BatchEnsemble 不仅在性能上逊于深度集成方法，而且在准确度、校准性和分布外检测方面与单一模型基线高度接近。在 MNIST 上进行的对照研究发现，其成员在函数空间和参数空间上近乎一致，表明其实现差异化预测模式的能力有限。因此，BatchEnsemble 的行为更接近于单一模型，而非真正的集成。