Deep Ensembles are a simple, reliable, and effective method of improving both the predictive performance and uncertainty estimates of deep learning approaches. However, they are widely criticised as being computationally expensive, due to the need to deploy multiple independent models. Recent work has challenged this view, showing that for predictive accuracy, ensembles can be more computationally efficient (at inference) than scaling single models within an architecture family. This is achieved by cascading ensemble members via an early-exit approach. In this work, we investigate extending these efficiency gains to tasks related to uncertainty estimation. As many such tasks, e.g. selective classification, are binary classification, our key novel insight is to only pass samples within a window close to the binary decision boundary to later cascade stages. Experiments on ImageNet-scale data across a number of network architectures and uncertainty tasks show that the proposed window-based early-exit approach is able to achieve a superior uncertainty-computation trade-off compared to scaling single models. For example, a cascaded EfficientNet-B2 ensemble is able to achieve similar coverage at 5% risk as a single EfficientNet-B4 with <30% the number of MACs. We also find that cascades/ensembles give more reliable improvements on OOD data vs scaling models up. Code for this work is available at: https://github.com/Guoxoug/window-early-exit.

翻译：深度集成是一种简单、可靠且有效的方法，能够同时提升深度学习方法的预测性能与不确定性估计质量。然而，该方法因需部署多个独立模型而被广泛批评为计算成本高昂。近期研究挑战了这一观点，表明在预测准确性方面，集成方法在推理阶段的计算效率可超越同一架构族内的单一模型缩放。这一优势是通过基于提前退出策略的集成成员级联实现的。本研究旨在将这种效率优势扩展到与不确定性估计相关的任务中。鉴于此类任务（如选择性分类）多为二分类问题，我们的关键创新在于：仅将处于二分类决策边界附近窗口内的样本传递至后续级联阶段。在ImageNet规模数据集上，针对多种网络架构与不确定性任务开展的实验表明，所提出的基于窗口的提前退出方法在不确定性-计算权衡方面优于单一模型缩放。例如，级联EfficientNet-B2集成在5%风险水平下可实现与单一EfficientNet-B4相当的覆盖率，而计算量（MACs）不足后者的30%。我们同时发现，相较于模型缩放，级联/集成方法在分布外（OOD）数据上能提供更可靠的性能提升。相关代码已开源：https://github.com/Guoxoug/window-early-exit。