A salient object segmentation framework using diffusion-based affinity learning

作者：

Highlights：

• A novel framework for saliency segmentation using affinity diffusion is proposed.

• A regularized diffusion process used for learning full transition matrix.

• The efficiency of two seminal affinity diffusion algorithms is evaluated.

• The comparable precision to deep learning-based methods is achieved.

摘要

•A novel framework for saliency segmentation using affinity diffusion is proposed.•A regularized diffusion process used for learning full transition matrix.•The efficiency of two seminal affinity diffusion algorithms is evaluated.•The comparable precision to deep learning-based methods is achieved.

论文关键词：Salient object segmentation,Absorbing Markov chain,Affinity graph learning,Diffusion process,Tensor product graph

论文评审过程：Received 22 June 2020, Revised 8 November 2020, Accepted 30 November 2020, Available online 5 December 2020, Version of Record 9 December 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114428