arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.13086stat.MLcs.CVcs.LGmath.STstat.TH
收藏

RankSEG:一种基于排序的一致性分割框架

RankSEG: A Consistent Ranking-based Framework for Segmentation

The Chinese University of Hong Kong(香港中文大学);University of Minnesota(明尼苏达大学)

Ben Dai, Chunlin Li

AI总结:

本文提出基于排序的一致性分割框架RankDice/RankIoU,解决现有阈值法在Dice/IoU指标下不一致的问题,并证明其校准性与收敛性,在多个数据集上验证了有效性。

摘要:

分割已成为计算机视觉和自然语言处理的基础领域,它为每个像素/特征分配一个标签,以从图像/文本中提取感兴趣的区域。为了评估分割性能,使用Dice和IoU指标来衡量真实分割与预测分割之间的重叠程度。在本文中,我们建立了关于Dice/IoU指标的分割理论基础,包括贝叶斯规则和Dice-/IoU-校准,类似于分类中的分类校准或Fisher一致性。我们证明了现有的基于阈值的框架与大多数操作损失在Dice/IoU指标下并不一致,因此可能导致次优解。为了解决这一缺陷,我们提出了一种新颖的基于排序的一致性框架,即RankDice/RankIoU,其灵感来自贝叶斯分割规则的插件规则。我们开发了三种具有GPU并行执行的数值算法,以在大规模和高维分割中实现所提出的框架。我们研究了所提出框架的统计性质。我们证明它是Dice-/IoU-校准的,并提供了其超额风险界限和收敛速率。RankDice/mRankDice的数值有效性在各种模拟示例以及具有最先进深度学习架构的Fine-annotated CityScapes、Pascal VOC和Kvasir-SEG数据集上得到了证明。

英文摘要:

Segmentation has emerged as a fundamental field of computer vision and natural language processing, which assigns a label to every pixel/feature to extract regions of interest from an image/text. To evaluate the performance of segmentation, the Dice and IoU metrics are used to measure the degree of overlap between the ground truth and the predicted segmentation. In this paper, we establish a theoretical foundation of segmentation with respect to the Dice/IoU metrics, including the Bayes rule and Dice-/IoU-calibration, analogous to classification-calibration or Fisher consistency in classification. We prove that the existing thresholding-based framework with most operating losses are not consistent with respect to the Dice/IoU metrics, and thus may lead to a suboptimal solution. To address this pitfall, we propose a novel consistent ranking-based framework, namely RankDice/RankIoU, inspired by plug-in rules of the Bayes segmentation rule. Three numerical algorithms with GPU parallel execution are developed to implement the proposed framework in large-scale and high-dimensional segmentation. We study statistical properties of the proposed framework. We show it is Dice-/IoU-calibrated, and its excess risk bounds and the rate of convergence are also provided. The numerical effectiveness of RankDice/mRankDice is demonstrated in various simulated examples and Fine-annotated CityScapes, Pascal VOC and Kvasir-SEG datasets with state-of-the-art deep learning architectures.

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。

↑