Quantifying uncertainty is important for actionable predictions in real-world applications. A crucial part of predictive uncertainty quantification is the estimation of epistemic uncertainty, which is defined as an integral of the product between a divergence function and the posterior. Current methods such as Deep Ensembles or MC dropout underperform at estimating the epistemic uncertainty, since they primarily consider the posterior when sampling models. We suggest Quantification of Uncertainty with Adversarial Models (QUAM) to better estimate the epistemic uncertainty. QUAM identifies regions where the whole product under the integral is large, not just the posterior. Consequently, QUAM has lower approximation error of the epistemic uncertainty compared to previous methods. Models for which the product is large correspond to adversarial models (not adversarial examples!). Adversarial models have both a high posterior as well as a high divergence between their predictions and that of a reference model. Our experiments show that QUAM excels in capturing epistemic uncertainty for deep learning models and outperforms previous methods on challenging tasks in the vision domain.

翻译：量化不确定性对于现实应用中的可操作预测至关重要。预测性不确定度量的一个关键部分是认知不确定性的估计，其定义为散度函数与后验概率乘积的积分。当前方法如深度集成或MC丢弃法在估计认知不确定性方面表现欠佳，因为它们在采样模型时主要考虑后验概率。我们提出基于对抗模型的量化不确定性（QUAM）以更准确地估计认知不确定性。QUAM能够识别积分下整个乘积较大的区域，而不仅仅关注后验概率。因此，QUAM相较于先前方法具有更低的认知不确定性近似误差。乘积较大的模型对应的是对抗模型（而非对抗样本！）。对抗模型兼具高后验概率及其预测与参考模型预测间的高散度。实验表明，QUAM在捕捉深度学习模型认知不确定性方面表现优异，并在视觉领域具有挑战性的任务上超越了现有方法。