Is segmentation uncertainty useful?
This work addresses the practical utility of uncertainty in segmentation for researchers and practitioners, but it is incremental as it evaluates existing methods without introducing new ones.
The paper investigates whether segmentation uncertainty from probabilistic models is useful for assessing segmentation quality and active learning, finding that uncertainty correlates with error but is not beneficial for active learning.
Probabilistic image segmentation encodes varying prediction confidence and inherent ambiguity in the segmentation problem. While different probabilistic segmentation models are designed to capture different aspects of segmentation uncertainty and ambiguity, these modelling differences are rarely discussed in the context of applications of uncertainty. We consider two common use cases of segmentation uncertainty, namely assessment of segmentation quality and active learning. We consider four established strategies for probabilistic segmentation, discuss their modelling capabilities, and investigate their performance in these two tasks. We find that for all models and both tasks, returned uncertainty correlates positively with segmentation error, but does not prove to be useful for active learning.