Abstract
Optical flow estimation can be formulated as an end-to-end supervised learning problem, which yields estimates with a superior accuracy-runtime tradeoff compared to alternative methodology. In this paper, we make such networks estimate their local uncertainty about the correctness of their prediction, which is vital information when building decisions on top of the estimations. For the first time we compare several strategies and techniques to estimate uncertainty in a large-scale computer vision task like optical flow estimation. Moreover, we introduce a new network architecture and loss function that enforce complementary hypotheses and provide uncertainty estimates efficiently with a single forward pass and without the need for sampling or ensembles. We demonstrate the quality of the uncertainty estimates, which is clearly above previous confidence measures on optical flow and allows for interactive frame rates.
Abstract (translated)
光流估计可以被表述为端到端监督学习问题，与替代方法相比，其产生具有更高精度 - 运行时权衡的估计。在本文中，我们使这样的网络估计它们的预测正确性的局部不确定性，这是在估计之上建立决策时的重要信息。我们首次比较了几种策略和技术来估算大规模计算机视觉任务（如光流估算）中的不确定性。此外，我们引入了一种新的网络架构和损失功能，可以强制实施补充假设，并通过单个正向传递有效地提供不确定性估计，而无需采样或集合。我们证明了不确定性估计的质量，这显然高于先前对光流的置信度测量，并允许交互式帧速率。
URL
https://arxiv.org/abs/1802.07095
