Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation

1 code implementation • CVPR 2022 • Tianfei Zhou, Meijie Zhang, Fang Zhao, Jianwu Li

Particularly, we propose i) semantic contrast to drive network learning by contrasting massive categorical object regions, leading to a more holistic object pattern understanding, and ii) semantic aggregation to gather diverse relational contexts in the memory to enrich semantic representations.

Object Weakly supervised Semantic Segmentation +1