Recent mainstream weakly-supervised semantic segmentation (WSSS) approaches mainly relies on image-level classification learning, which has limited representation capacity. In this paper, we propose a novel semantic learning based framework, named SLAMs (Semantic Learning based Activation Map), for WSSS.
翻译:最近主流监督不力的语义分割法(SSS)主要依赖图像级分类学习,而图像级分类学习代表能力有限。 在本文中,我们提议为SSS提出一个新的语义学习基础框架,名为Semanic Learning Magraphation(Semanic Learning Map ), 名为Semanic Learning Maget(Semanic Learning Map ) 。