Joint Topology-preserving and Feature-refinement Network for Curvilinear Structure Segmentation
Authors:
- 1 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7127-7136
Abstract
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-wise features are two critical aspects of CSS. However, most semantic segmentation methods only focus on enhancing feature representations while existing CSS techniques emphasize preserving topology alone. In this paper, we present a Joint Topology-preserving and Feature-refinement Network (JTFN) that jointly models global topology and refined features based on an iterative feedback learning strategy. Specifically, we explore the structure of objects to help preserve corresponding topologies of predicted masks, thus design a reciprocative two-stream module for CSS and boundary detection. In addition, we introduce such topology-aware predictions as feedback guidance that refines attentive features by supplementing and enhancing saliencies. To the best of our knowledge, this is the first work that jointly addresses topology preserving and feature refinement for CSS. We evaluate JTFN on four datasets of diverse applications: Crack500, CrackTree200, Roads, and DRIVE. Results show that JTFN performs best in comparison with alternative methods. Code is available. 1Keywords
This publication has 41 references indexed in Scilit:
- Holistically-Nested Edge Detection2015
- Fully convolutional networks for semantic segmentation2015
- Learning Fully-Connected CRFs for Blood Vessel Segmentation in Retinal Images2014
- Detecting Irregular Curvilinear Structures in Gray Scale and Color Imagery Using Multi-directional Oriented Flux2013
- Structured Forests for Fast Edge Detection2013
- Image Segmentation with Cascaded Hierarchical Models and Logistic Disjunctive Normal Networks2013
- Supervised Feature Learning for Curvilinear Structure Segmentation2013
- CrackTree: Automatic crack detection from pavement imagesPattern Recognition Letters, 2012
- Three Dimensional Curvilinear Structure Detection Using Optimally Oriented Flux2008
- Boundary recognition in sensor networks by topological methods2006