双曲空间中面向开放世界感知的类别感知持续语义分割
Taxonomy-Aware Continual Semantic Segmentation in Hyperbolic Spaces for Open-World Perception
AI总结：
针对开放世界语义分割中旧类刚性限制问题，提出基于双曲空间类别学树结构的TOPICS方法，实现类别增量学习，在Cityscapes和Mapillary Vistas 2.0上达到最先进性能。
摘要：
语义分割模型通常在固定的类别集合上训练，这限制了它们在开放世界场景中的适用性。类别增量式语义分割旨在用新出现的类别更新模型，同时防止对先前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限制，降低了它们学习新增量类别的有效性。在本工作中，我们提出了面向类别学导向的庞加莱正则化增量类别分割（TOPICS），该方法在双曲空间中遵循显式的类别学树结构学习特征嵌入。这种监督为旧类别提供了可塑性，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维护隐式的类别关系约束。这确保了潜在空间能够持续适应新约束，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个现实的增量学习协议，其中新类别可以源自已知类别或背景。在Cityscapes和Mapillary Vistas 2.0基准上对TOPICS的广泛评估表明，它达到了最先进的性能。我们在http://topics.cs.uni-freiburg.de公开提供代码和训练好的模型。
英文摘要：
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 Poincaré-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 Poincaré 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.
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。
