Single annotated pixel based weakly supervised semantic segmentation under driving scenes

作者：

Highlights：

• A novel lightweight weakly supervised task setting for driving scenes understanding.

• Implement objects and scenes better representation with semantic and imaging feature.

• An alternative iteration structure for fusing intra and inter image learning.

• A complete framework to solve weakly supervised tasks under complex driving scenes.

摘要

•A novel lightweight weakly supervised task setting for driving scenes understanding.•Implement objects and scenes better representation with semantic and imaging feature.•An alternative iteration structure for fusing intra and inter image learning.•A complete framework to solve weakly supervised tasks under complex driving scenes.

论文关键词：Weakly supervised condition,Semantic segmentation,Complex driving scenes,Optimal feature setting

论文评审过程：Received 11 October 2020, Revised 7 March 2021, Accepted 29 March 2021, Available online 6 April 2021, Version of Record 12 April 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107979