Weakly-supervised semantic segmentation with superpixel guided local and global consistency

作者：

Highlights：

• An introduction of superpixel knowledge into affinity based segmentation approach.

• An iterative framework that achieve an effective collaboration of the superpixel information. and the features of semantic segmentation.

• A satisfactory performance on the PASCAL VOC dataset compared with the state of the art models.

摘要

•An introduction of superpixel knowledge into affinity based segmentation approach.•An iterative framework that achieve an effective collaboration of the superpixel information. and the features of semantic segmentation.•A satisfactory performance on the PASCAL VOC dataset compared with the state of the art models.

论文关键词：Weakly supervised condition,Semantic segmentation,Pixel-level affinity,Superpixel

论文评审过程：Received 6 July 2021, Revised 6 December 2021, Accepted 20 December 2021, Available online 23 December 2021, Version of Record 2 January 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108504