面向激光雷达语义分割的持续学习：稀疏数据上的类别增量与由粗到精策略
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data
AI总结：
本文首次开展LiDAR点云语义分割的类别增量持续学习研究，适配多种持续学习策略应对微调与由粗到精学习场景，在SemanticKITTI上的表现比肩前沿方法与离线学习。
摘要：
过去几年，针对图像分类和分割的持续学习（CL）策略已被广泛研究，研究者设计了知识蒸馏、自修复等创新方案来应对灾难性遗忘问题。然而，持续学习范式在点云上的应用仍未被探索，亟需相关研究，尤其是采用能捕捉LiDAR数据稀疏性与分布不均特性的架构的研究。本文分析了应用于点云语义分割的类别增量学习问题，对比了多种方法与前沿架构。据我们所知，这是首个针对LiDAR点云语义分割的类别增量持续学习研究。我们将不同的CL策略适配到LiDAR点云并开展测试，同时应对经典微调场景和由粗到精（Coarse-to-Fine）学习范式。该框架已在SemanticKITTI数据集上通过两种不同架构进行评估，所得结果与前沿CL策略及标准离线学习的结果相当。
英文摘要：
During the last few years, continual learning (CL) strategies for image classification and segmentation have been widely investigated designing innovative solutions to tackle catastrophic forgetting, like knowledge distillation and self-inpainting. However, the application of continual learning paradigms to point clouds is still unexplored and investigation is required, especially using architectures that capture the sparsity and uneven distribution of LiDAR data. The current paper analyzes the problem of class incremental learning applied to point cloud semantic segmentation, comparing approaches and state-of-the-art architectures. To the best of our knowledge, this is the first example of class-incremental continual learning for LiDAR point cloud semantic segmentation. Different CL strategies were adapted to LiDAR point clouds and tested, tackling both classic fine-tuning scenarios and the Coarse-to-Fine learning paradigm. The framework has been evaluated through two different architectures on SemanticKITTI, obtaining results in line with state-of-the-art CL strategies and standard offline learning.
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。
