Segmentation uncertainty models predict a distribution over plausible segmentations for a given input, which they learn from the annotator variation in the training set. However, in practice these annotations can differ systematically in the way they are generated, for example through the use of different labeling tools. This results in datasets that contain both data variability and differing label styles. In this paper, we demonstrate that applying state-of-the-art segmentation uncertainty models on such datasets can lead to model bias caused by the different label styles. We present an updated modelling objective conditioning on labeling style for aleatoric uncertainty estimation, and modify two state-of-the-art-architectures for segmentation uncertainty accordingly. We show with extensive experiments that this method reduces label style bias, while improving segmentation performance, increasing the applicability of segmentation uncertainty models in the wild. We curate two datasets, with annotations in different label styles, which we will make publicly available along with our code upon publication.

翻译：分割不确定性模型可以预测一个给定输入的可能分割情况，并从训练集的标注变异中学习到分布。然而，在实践中这些标注可以以不同的方式生成，例如通过使用不同的标注工具。这导致数据集既包含数据变异性又包含不同的标签风格。在本文中，我们展示了应用最先进的分割不确定性模型在这些数据集上可能导致的模型偏差，这种偏差是由于不同的标签风格造成的。我们提出了一个更新的建模目标，该目标针对标签样式进行条件化，以进行不确定性评估，并相应修改了两种最先进的分割不确定性体系结构。我们进行了广泛的实验，表明该方法减少了标签风格的偏差，同时提高了分割性能，增加了分割不确定性模型在现实中的适用性。我们还策划了两个包含不同标签风格注释的数据集，待发表时我们将公开发布这些数据集以及我们的代码。