Semantic segmentation models are typically trained on a fixed set of classes, limiting their applicability in open-world scenarios. Class-incremental semantic segmentation aims to update models with emerging new classes while preventing catastrophic forgetting of previously learned ones. However, existing methods impose strict rigidity on old classes, reducing their effectiveness in learning new incremental classes. In this work, we propose Taxonomy-Oriented Poincar\'e-regularized Incremental-Class Segmentation (TOPICS) that learns feature embeddings in hyperbolic space following explicit taxonomy-tree structures. This supervision provides plasticity for old classes, updating ancestors based on new classes while integrating new classes at fitting positions. Additionally, we maintain implicit class relational constraints on the geometric basis of the Poincar\'e ball. This ensures that the latent space can continuously adapt to new constraints while maintaining a robust structure to combat catastrophic forgetting. We also establish eight realistic incremental learning protocols for autonomous driving scenarios, where novel classes can originate from known classes or the background. Extensive evaluations of TOPICS on the Cityscapes and Mapillary Vistas 2.0 benchmarks demonstrate that it achieves state-of-the-art performance. We make the code and trained models publicly available at http://topics.cs.uni-freiburg.de.

翻译：语义分割模型通常在固定类别集合上进行训练，这限制了其在开放世界场景中的适用性。类别增量语义分割旨在利用新出现的类别更新模型，同时防止对先前已学习类别的灾难性遗忘。然而，现有方法对旧类别施加了严格的刚性约束，降低了其学习新增量类别的有效性。在本工作中，我们提出了面向分类学的庞加莱正则化增量类别分割方法，该方法遵循显式的分类树结构在双曲空间中学习特征嵌入。这种监督为旧类别提供了可塑性，能够基于新类别更新祖先节点，同时将新类别整合到合适的位置。此外，我们在庞加莱球的几何基础上保持了隐式的类别关系约束。这确保了潜在空间能够持续适应新的约束，同时保持稳健的结构以对抗灾难性遗忘。我们还为自动驾驶场景建立了八种现实的增量学习协议，其中新类别可能源自已知类别或背景。在Cityscapes和Mapillary Vistas 2.0基准测试上对TOPICS进行的广泛评估表明，其达到了最先进的性能。我们将代码和训练好的模型公开发布在 http://topics.cs.uni-freiburg.de。