arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.16265cs.CV
收藏

分割不确定性有用吗?

Is segmentation uncertainty useful?

University of Copenhagen(哥本哈根大学);Technical University of Denmark(丹麦技术大学)

Steffen Czolbe, Kasra Arnavaz, Oswin Krause, Aasa Feragen

摘要:

概率图像分割编码不同的预测置信度和分割问题中固有的模糊性。虽然不同的概率分割模型的目的是捕捉不同方面的分割不确定性和模糊性,这些建模的差异很少讨论的不确定性的应用程序的上下文中。我们考虑分割不确定性的两个常见用例,即分割质量评估和主动学习。我们认为四个既定的策略概率分割,讨论他们的建模能力,并调查他们在这两个任务的表现。我们发现,对于所有的模型和两个任务,返回的不确定性与分割误差呈正相关,但并没有证明是有用的主动学习。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑