arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.03299cs.CV
收藏

一种使用拟共形映射的、基于学习的拓扑保持分割框架

A Learning-based Framework for Topology-Preserving Segmentation using Quasiconformal Mappings

City University of Hong Kong(香港城市大学);Chinese University of Hong Kong(香港中文大学)

Han Zhang, Lok Ming Lui

AI总结:

本文提出基于变形与拟共形理论的 TPSN,通过变形估计和 Beltrami 调整保持分割掩膜拓扑,并支持无监督训练,在多数据集上取得更优准确率。

摘要:

我们提出了 Topology-Preserving Segmentation Network(拓扑保持分割网络,TPSN),这是一种基于变形的模型,能够在提取图像中对象的同时保持其拓扑属性。该网络生成与模板掩膜具有相同拓扑的分割掩膜,即使在使用有限数据进行训练时也是如此。该网络由两个组件组成:Deformation Estimation Network(变形估计网络),它生成一个变形图,将模板掩膜扭曲以包围感兴趣区域;以及 Beltrami Adjustment Module(Beltrami 调整模块),它基于拟共形理论,通过截断相关的 Beltrami 系数来确保变形图的双射性。所提出的网络还可以以无监督方式训练,从而消除对带标签训练数据的需求,这是通过引入无监督分割损失实现的。我们在多个图像数据集上的实验结果表明,TPSN 在拓扑正确的情况下取得了优于最先进模型的分割准确率。此外,我们还展示了 TPSN 处理多对象分割的能力。

英文摘要:

We propose the Topology-Preserving Segmentation Network, a deformation-based model that can extract objects in an image while maintaining their topological properties. This network generates segmentation masks that have the same topology as the template mask, even when trained with limited data. The network consists of two components: the Deformation Estimation Network, which produces a deformation map that warps the template mask to enclose the region of interest, and the Beltrami Adjustment Module, which ensures the bijectivity of the deformation map by truncating the associated Beltrami coefficient based on Quasiconformal theories. The proposed network can also be trained in an unsupervised manner, eliminating the need for labeled training data. This is achieved by incorporating an unsupervised segmentation loss. Our experimental results on various image datasets show that TPSN achieves better segmentation accuracy than state-of-the-art models with correct topology. Furthermore, we demonstrate TPSN's ability to handle multiple object segmentation.

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。

↑