物以类聚：领域自适应分割的类别发散指导
Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation
摘要：
无监督领域自适应（UDA）的目的是提高模型从源域到目标域的泛化能力。现有的UDA模型主要关注于通过最小化源域和目标域之间的特征差异来缓解域迁移，但通常忽略了类混淆问题。在这项工作中，我们提出了一个类间分离和类内聚合（ISIA）机制。它鼓励跨领域的代表性之间的一致性相同的类别和不同类别之间的差异。通过这种方式，属于相同类别的特征被对齐在一起，并且易混淆的类别被分离。通过度量每个类别的对齐复杂度，我们设计了一个自适应加权实例匹配（AIM）策略，以进一步优化实例级自适应。基于我们提出的方法，我们还提出了一个层次化的无监督的跨领域语义分割任务的领域自适应框架。通过图像级、特征级、类别级和实例级的对齐，实现了模型从源域到目标域的更强泛化性能。在两个典型的跨域语义分割任务中，GTA5到Cityscapes和SYNTHIA到Cityscapes，我们的方法达到了最先进的分割精度。我们还建立了两个跨领域的语义分割数据集的基础上公开可用的数据，即，遥感建筑物分割和道路分割，进行区域自适应分割。
英文摘要：
Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain. Present UDA models focus on alleviating the domain shift by minimizing the feature discrepancy between the source domain and the target domain but usually ignore the class confusion problem. In this work, we propose an Inter-class Separation and Intra-class Aggregation (ISIA) mechanism. It encourages the cross-domain representative consistency between the same categories and differentiation among diverse categories. In this way, the features belonging to the same categories are aligned together and the confusable categories are separated. By measuring the align complexity of each category, we design an Adaptive-weighted Instance Matching (AIM) strategy to further optimize the instance-level adaptation. Based on our proposed methods, we also raise a hierarchical unsupervised domain adaptation framework for cross-domain semantic segmentation task. Through performing the image-level, feature-level, category-level and instance-level alignment, our method achieves a stronger generalization performance of the model from the source domain to the target domain. In two typical cross-domain semantic segmentation tasks, i.e., GTA5 to Cityscapes and SYNTHIA to Cityscapes, our method achieves the state-of-the-art segmentation accuracy. We also build two cross-domain semantic segmentation datasets based on the publicly available data, i.e., remote sensing building segmentation and road segmentation, for domain adaptive segmentation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
