Though image-level weakly supervised semantic segmentation (WSSS) has
achieved great progress with Class Activation Maps (CAMs) as the cornerstone,
the large supervision gap between classification and segmentation still hampers
the model to generate more complete and precise pseudo masks for segmentation.
In this study, we propose weakly-supervised pixel-to-prototype contrast that
can provide pixel-level supervisory signals to narrow the gap. Guided by two
intuitive priors, our method is executed across different views and within per
single view of an image, aiming to impose cross-view feature semantic
consistency regularization and facilitate intra(inter)-class
compactness(dispersion) of the feature space. Our method can be seamlessly
incorporated into existing WSSS models without any changes to the base networks
and does not incur any extra inference burden. Extensive experiments manifest
that our method consistently improves two strong baselines by large margins,
demonstrating the effectiveness. Specifically, built on top of SEAM, we improve
the initial seed mIoU on PASCAL VOC 2012 from 55.4% to 61.5%. Moreover, armed
with our method, we increase the segmentation mIoU of EPS from 70.8% to 73.6%,
achieving new state-of-the-art.

本文提出了一种基于像素级原型对比度的弱监督语义分割方法，通过两种直观的先验知识，对图像的不同视角和单个视角内进行执行，旨在实施跨视图特征语义一致性规则，并促进特征空间的内部（间）类一致性（离散度），从而提高了两个强基线模型的精度，并在 PASCAL VOC 2012 上实现了新的最先进水平。