paper-with-me

Papers

Topology-Preserving Deep Image Segmentation

2019-06-12 · NeurIPS 2019 12 · Xiaoling Hu, Li Fuxin, Dimitris Samaras, Chao Chen

Segmentation algorithms are prone to make topological errors on fine-scale structures, e.g., broken connections. We propose a novel method that learns to segment with correct topology. In particular, we design a continuous-valued loss function that enforces a segmentation to have the same topology as the ground truth, i.e., having the same Betti number. The proposed topology-preserving loss function is differentiable and we incorporate it into end-to-end training of a deep neural network. Our method achieves much better performance on the Betti number error, which directly accounts for the topological correctness. It also performs superiorly on other topology-relevant metrics, e.g., the Adjusted Rand Index and the Variation of Information. We illustrate the effectiveness of the proposed method on a broad spectrum of natural and biomedical datasets.

📄 PDF Abstract BibTeX arXiv:1906.05404

Code (4)

HuXiaoling/TopoLoss 공식 구현 pytorch
alexanderhberger/multiclass-bettimatching jax
alexanderhberger/topo-pitfalls jax
nstucki/betti-matching pytorch

Tasks

Image SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Topology-Preserving Segmentation Network: A Deep Learning Segmentation Framework for Connected Component

2022-02-27 · Han Zhang, Lok Ming Lui

Medical image segmentation, which aims to automatically extract anatomical or pathological structures, plays a key role in computer-aided diagnosis and disease analysis. Despite the problem has been widely studied, exist…

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation+1

Topology-Preserving 3D Image Segmentation Based On Hyperelastic Regularization

2021-03-31 · Daoping Zhang, Lok Ming Lui

Image segmentation is to extract meaningful objects from a given image. For degraded images due to occlusions, obscurities or noises, the accuracy of the segmentation result can be severely affected. To alleviate this pr…

Image SegmentationSegmentationSemantic Segmentation

Topology preserving Image segmentation using the iterative convolution-thresholding method

2025-03-22 · Lingyun Deng, Litong Liu, Dong Wang, Xiao-Ping Wang

Variational models are widely used in image segmentation, with various models designed to address different types of images by optimizing specific objective functionals. However, traditional segmentation models primarily…

Image SegmentationSegmentationSemantic Segmentation

BuyTheDips: PathLoss for improved topology-preserving deep learning-based image segmentation

2022-07-23 · Minh On Vu Ngoc, Yizi Chen, Nicolas Boutry, Jonathan Fabrizio 외

Capturing the global topology of an image is essential for proposing an accurate segmentation of its domain. However, most of existing segmentation methods do not preserve the initial topology of the given input, which i…

Image SegmentationSegmentationSemantic Segmentation

Joint Topology-Preserving and Feature-Refinement Network for Curvilinear Structure Segmentation

2021-01-01 · ICCV 2021 10 · Mingfei Cheng, Kaili Zhao, Xuhong Guo, Yajing Xu 외

Curvilinear structure segmentation (CSS) is under semantic segmentation, whose applications include crack detection, aerial road extraction, and biomedical image segmentation. In general, geometric topology and pixel…

Boundary DetectionImage SegmentationSegmentationSemantic Segmentation