Image classification with neural networks (NNs) is widely used in industrial processes, situations where the model likely encounters unknown objects during deployment, i.e., out-of-distribution (OOD) data. Worryingly, NNs tend to make confident yet incorrect predictions when confronted with OOD data. To increase the models' reliability, they should quantify the uncertainty in their own predictions, communicating when the output should (not) be trusted. Deep ensembles, composed of multiple independent NNs, have been shown to perform strongly but are computationally expensive. Recent research has proposed more efficient NN ensembles, namely the snapshot, batch, and multi-input multi-output ensemble. This study investigates the predictive and uncertainty performance of efficient NN ensembles in the context of image classification for industrial processes. It is the first to provide a comprehensive comparison and it proposes a novel Diversity Quality metric to quantify the ensembles' performance on the in-distribution and OOD sets in one single metric. The results highlight the batch ensemble as a cost-effective and competitive alternative to the deep ensemble. It matches the deep ensemble in both uncertainty and accuracy while exhibiting considerable savings in training time, test time, and memory storage.

翻译：神经网络图像分类广泛应用于工业流程中，但模型在部署时很可能遇到未知物体，即分布外数据。令人担忧的是，神经网络在面对分布外数据时往往做出自信但错误的预测。为提高模型可靠性，模型应量化自身预测的不确定性，以传达输出何时（不）应被信任。由多个独立神经网络组成的深度集成方法虽表现出色但计算成本高昂。近期研究提出了更高效的神经网络集成方法，包括快照集成、批量集成和多输入多输出集成。本研究探讨了高效神经网络集成在工业流程图像分类中的预测性能与不确定性表现，首次提供了全面比较，并提出新颖的多样性质量指标，以单一度量量化集成方法在分布内和分布外数据集上的综合性能。结果表明批量集成是深度集成具有成本效益的竞争性替代方案，其在不确定性与准确性方面均与深度集成相当，同时在训练时间、测试时间和内存存储方面实现显著节约。