Weakly-supervised semantic segmentation (WSSS) performs pixel-wise classification given only image-level labels for training. Despite the difficulty of this task, the research community has achieved promising results over the last five years. Still, current WSSS literature misses the detailed sense of how well the methods perform on different sizes of objects. Thus we propose a novel evaluation metric to provide a comprehensive assessment across different object sizes and collect a size-balanced evaluation set to complement PASCAL VOC. With these two gadgets, we reveal that the existing WSSS methods struggle in capturing small objects. Furthermore, we propose a size-balanced cross-entropy loss coupled with a proper training strategy. It generally improves existing WSSS methods as validated upon ten baselines on three different datasets.

弱监督语义分割方法在不具备像素级标签的训练数据下，通过只有图像级标签进行像素级分类。本文通过提出新的评估指标和收集一个大小平衡的评估集，揭示了现有弱监督语义分割方法在捕捉小物体方面的困难，并提出了一个大小平衡的交叉熵损失函数和适当的训练策略，从而改进现有方法在三个不同数据集上的性能。

弱监督语义分割中的小物体重要性