arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.10678cs.CVcs.LG
收藏

用于实例分割的概率深度学习

Probabilistic Deep Learning for Instance Segmentation

Charité University Hospital(夏里特大学医院);Max Delbrück Center for Molecular Medicine(马克斯·德尔布吕克分子医学中心);Berlin Institute of Health(柏林健康研究所)

Josef Lorenz Rumberger, Lisa Mais, Dagmar Kainmueller

摘要:

概率卷积神经网络预测预测分布而不是点估计,导致了计算机视觉许多领域的最新进展,从图像重建到语义分割。除了最先进的基准结果外,这些网络还可以量化预测中的局部不确定性。这些被用在主动学习框架中,以针对专业注释者的标记工作或评估安全关键环境中的预测质量。然而,对于实例分割问题,这些方法迄今为止并不经常使用。我们试图缩小这一差距,提出了一个通用的方法来获得模型固有的不确定性估计内无提案实例分割模型。此外,我们分析了质量的不确定性估计与适应从语义分割的度量。我们在BBBC010 C上评估了我们的方法。elegans数据集,在那里它产生了有竞争力的性能,同时还预测了不确定性估计,这些估计携带了关于对象级不准确性的信息,如错误分割和错误合并。我们进行了模拟,以显示潜在的使用这种不确定性估计在指导校对。

英文摘要:

Probabilistic convolutional neural networks, which predict distributions of predictions instead of point estimates, led to recent advances in many areas of computer vision, from image reconstruction to semantic segmentation. Besides state of the art benchmark results, these networks made it possible to quantify local uncertainties in the predictions. These were used in active learning frameworks to target the labeling efforts of specialist annotators or to assess the quality of a prediction in a safety-critical environment. However, for instance segmentation problems these methods are not frequently used so far. We seek to close this gap by proposing a generic method to obtain model-inherent uncertainty estimates within proposal-free instance segmentation models. Furthermore, we analyze the quality of the uncertainty estimates with a metric adapted from semantic segmentation. We evaluate our method on the BBBC010 C.\ elegans dataset, where it yields competitive performance while also predicting uncertainty estimates that carry information about object-level inaccuracies like false splits and false merges. We perform a simulation to show the potential use of such uncertainty estimates in guided proofreading.

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。

↑