Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of their successive outputs is highly correlated with the accuracy of the value to which they converge. Thus, we can use the convergence rate as a useful proxy for uncertainty. This results in an approach to uncertainty estimation that provides state-of-the-art estimates at a much lower computational cost than techniques like Ensembles, and without requiring any modifications to the original iterative model. We demonstrate its practical value by embedding it in two application domains: road detection in aerial images and the estimation of aerodynamic properties of 2D and 3D shapes.

翻译：将直通式网络架构转化为迭代式架构（即利用自身输出作为输入）是提升性能的经典方法。本文论证了此类架构的额外优势：其连续输出值的收敛速率与收敛目标值的精度高度相关。因此，可将收敛速率作为不确定性的有效代理指标。该不确定性估计方法能以远低于集成学习等技术的计算成本提供最先进的估计结果，且无需对原始迭代模型进行任何修改。通过将其嵌入两个应用领域——航空图像道路检测与二维/三维形状气动特性估计——我们验证了该方法的实用价值。