Image-level weakly supervised semantic segmentation has received increasing attention due to its low annotation cost. Existing methods mainly rely on Class Activation Mapping (CAM) to obtain pseudo-labels for training semantic segmentation models. In this work, we are the first to demonstrate that long-tailed distribution in training data can cause the CAM calculated through classifier weights over-activated for head classes and under-activated for tail classes due to the shared features among head- and tail- classes. This degrades pseudo-label quality and further influences final semantic segmentation performance. To address this issue, we propose a Shared Feature Calibration (SFC) method for CAM generation. Specifically, we leverage the class prototypes that carry positive shared features and propose a Multi-Scaled Distribution-Weighted (MSDW) consistency loss for narrowing the gap between the CAMs generated through classifier weights and class prototypes during training. The MSDW loss counterbalances over-activation and under-activation by calibrating the shared features in head-/tail-class classifier weights. Experimental results show that our SFC significantly improves CAM boundaries and achieves new state-of-the-art performances. The project is available at https://github.com/Barrett-python/SFC.

翻译：图像级弱监督语义分割因其低标注成本而受到越来越多的关注。现有方法主要依赖类激活映射（CAM）获取伪标签，以训练语义分割模型。本文首次证明，训练数据中的长尾分布会导致通过分类器权重计算的CAM在头部类上过度激活，在尾部类上激活不足，这是由于头部类和尾部类之间存在共享特征。这会降低伪标签质量，并进一步影响最终的语义分割性能。为解决这一问题，我们提出了一种用于CAM生成的共享特征校准（SFC）方法。具体而言，我们利用携带正共享特征的类原型，并引入多尺度分布加权（MSDW）一致性损失，以在训练过程中缩小通过分类器权重和类原型生成的CAM之间的差距。MSDW损失通过校准头部/尾部类分类器权重中的共享特征，来平衡过度激活和激活不足的问题。实验结果表明，我们的SFC显著改善了CAM边界，并取得了新的最先进性能。项目代码请访问 https://github.com/Barrett-python/SFC。