Saved in:
Bibliographic Details
Main Authors: Bransby, Kit Mills, Slabaugh, Greg, Bourantas, Christos, Zhang, Qianni
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.12155
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866907802684882944
author Bransby, Kit Mills
Slabaugh, Greg
Bourantas, Christos
Zhang, Qianni
author_facet Bransby, Kit Mills
Slabaugh, Greg
Bourantas, Christos
Zhang, Qianni
contents We present a novel methodology that combines graph and dense segmentation techniques by jointly learning both point and pixel contour representations, thereby leveraging the benefits of each approach. This addresses deficiencies in typical graph segmentation methods where misaligned objectives restrict the network from learning discriminative vertex and contour features. Our joint learning strategy allows for rich and diverse semantic features to be encoded, while alleviating common contour stability issues in dense-based approaches, where pixel-level objectives can lead to anatomically implausible topologies. In addition, we identify scenarios where correct predictions that fall on the contour boundary are penalised and address this with a novel hybrid contour distance loss. Our approach is validated on several Chest X-ray datasets, demonstrating clear improvements in segmentation stability and accuracy against a variety of dense- and point-based methods. Our source code is freely available at: www.github.com/kitbransby/Joint_Graph_Segmentation
format Preprint
id arxiv_https___arxiv_org_abs_2306_12155
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Joint Dense-Point Representation for Contour-Aware Graph Segmentation
Bransby, Kit Mills
Slabaugh, Greg
Bourantas, Christos
Zhang, Qianni
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
We present a novel methodology that combines graph and dense segmentation techniques by jointly learning both point and pixel contour representations, thereby leveraging the benefits of each approach. This addresses deficiencies in typical graph segmentation methods where misaligned objectives restrict the network from learning discriminative vertex and contour features. Our joint learning strategy allows for rich and diverse semantic features to be encoded, while alleviating common contour stability issues in dense-based approaches, where pixel-level objectives can lead to anatomically implausible topologies. In addition, we identify scenarios where correct predictions that fall on the contour boundary are penalised and address this with a novel hybrid contour distance loss. Our approach is validated on several Chest X-ray datasets, demonstrating clear improvements in segmentation stability and accuracy against a variety of dense- and point-based methods. Our source code is freely available at: www.github.com/kitbransby/Joint_Graph_Segmentation
title Joint Dense-Point Representation for Contour-Aware Graph Segmentation
topic Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2306.12155