论文标题
Bacoun：贝叶斯分类器的分布不确定性
BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty
论文作者
论文摘要
深层分类器的传统培训产生了过度自信的模型，这些模型在数据集转移下不可靠。我们提出了一个贝叶斯框架，以获得深层分类器的可靠不确定性估计。我们的方法包括一个插件的“生成器”，用于增强数据的其他类别的点，这些点位于训练数据的边界上，然后是贝叶斯推断，对特征的顶部进行了训练以区分这些“分布之外”点。
Traditional training of deep classifiers yields overconfident models that are not reliable under dataset shift. We propose a Bayesian framework to obtain reliable uncertainty estimates for deep classifiers. Our approach consists of a plug-in "generator" used to augment the data with an additional class of points that lie on the boundary of the training data, followed by Bayesian inference on top of features that are trained to distinguish these "out-of-distribution" points.
