Label group diffusion for image and image pair segmentation

作者：

Highlights：

• Multivariate relationships are explored for segmentation task based on a unary probability conversion model.

• A multi-relational learning method is proposed to estimate the label group information on TPG, which imposes a higher-order graph Laplacian to smooth the prior label.

• A generalized LGD framework is established for semi-supervised image segmentation and unsupervised image pair co-segmentation tasks.

摘要

•Multivariate relationships are explored for segmentation task based on a unary probability conversion model.•A multi-relational learning method is proposed to estimate the label group information on TPG, which imposes a higher-order graph Laplacian to smooth the prior label.•A generalized LGD framework is established for semi-supervised image segmentation and unsupervised image pair co-segmentation tasks.

论文关键词：Image segmentation,Image pair co-segmentation,Label group diffusion,Geometry manifold,Tensor product graph

论文评审过程：Received 18 October 2019, Revised 30 March 2020, Accepted 7 December 2020, Available online 17 December 2020, Version of Record 23 December 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107789