Domain-adaptive semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. However, existing methods primarily focus on directly learning categorically discriminative target features for segmenting target images, which is challenging in the absence of target labels. This work provides a new perspective. We ob serve that the features learned with source data manage to keep categorically discriminative during training, thereby enabling us to implicitly learn adequate target representations by simply pulling target features close to source features for each category. To this end, we propose T2S-DA, which encourages the model to learn similar cross-domain features. Also, considering the pixel categories are heavily imbalanced for segmentation datasets, we come up with a dynamic re-weighting strategy to help the model concentrate on those underperforming classes. Extensive experiments confirm that T2S-DA learns a more discriminative and generalizable representation, significantly surpassing the state-of-the-art. We further show that T2S-DA is quite qualified for the domain generalization task, verifying its domain-invariant property.

域自适应语义分割旨在将知识从标记的源域转移到未标记的目标域。然而，现有的方法主要集中在直接学习分类判别性目标特征来分割目标图像，这在没有目标标签的情况下是具有挑战性的。这项工作提供了一个新的视角。我们观察到，使用源数据学习的特征在训练过程中设法保持绝对判别性，从而使我们能够通过简单地将目标特征拉近每个类别的源特征来隐式地学习足够的目标表示。为此，我们提出了 T2S-DA，它鼓励模型学习类似的跨域特征。此外，考虑到分割数据集的像素类别严重不平衡，我们提出了一种动态重新加权策略，以帮助模型专注于那些表现不佳的类别。广泛的实验证实，T2S-DA 学习了更具辨别力和可推广性的表示，大大超过了最先进的。我们进一步表明，T2S-DA 完全有资格完成域泛化任务，验证其域不变性。