Mining precise class-aware attention maps, a.k.a, class activation maps, is essential for weakly supervised semantic segmentation. In this paper, we present L2G, a simple online local-to-global knowledge transfer framework for high-quality object attention mining. We observe that classification models can discover object regions with more details when replacing the input image with its local patches. Taking this into account, we first leverage a local classification network to extract attentions from multiple local patches randomly cropped from the input image. Then, we utilize a global network to learn complementary attention knowledge across multiple local attention maps online. Our framework conducts the global network to learn the captured rich object detail knowledge from a global view and thereby produces high-quality attention maps that can be directly used as pseudo annotations for semantic segmentation networks. Experiments show that our method attains 72.1% and 44.2% mIoU scores on the validation set of PASCAL VOC 2012 and MS COCO 2014, respectively, setting new state-of-the-art records. Code is available at https://github.com/PengtaoJiang/L2G.

本文提出了以 L2G 为核心的方法，通过本地分类网络从输入图像中随机获取多个局部路径进行注意提取，然后利用全局网络在线学习多个局部注意映射之间的互补关系，从全局视角学习对象的详细知识，从而产生高质量的注意地图，并将其直接用作语义分割网络的伪注释。

L2G: 一个简单的局部到全局的知识迁移框架，用于弱监督语义分割