基于几何结构的3D标签传播，提升自动驾驶激光雷达语义分割的跨域泛化能力
3DLabelProp: Geometric-Driven Domain Generalization for LiDAR Semantic Segmentation in Autonomous Driving
- 利用激光雷达传感器的顺序结构设计几何驱动的标签传播机制
- 在7个数据集上实现当前最优跨域性能，显著优于传统方法
- 特别适合对训练成本高或需强鲁棒性的自动驾驶感知系统
领域泛化旨在使深度学习模型在训练与推理数据存在显著分布差异时仍能保持性能，这对训练成本高或需强鲁棒性的模型尤为重要。自动驾驶中的激光雷达感知正面临这一挑战，催生了多种方法。本文提出一种基于几何结构的方法——3DLabelProp，利用激光雷达传感器的顺序特性，区别于主流的学习型方法。该方法应用于激光雷达语义分割（LSS）任务，在七个数据集上通过大量实验验证，表现达到当前最优水平，显著优于基线及现有领域泛化方法。
原文摘要 · Abstract (English)
Domain generalization aims to find ways for deep learning models to maintain their performance despite significant domain shifts between training and inference datasets. This is particularly important for models that need to be robust or are costly to train. LiDAR perception in autonomous driving is impacted by both of these concerns, leading to the emergence of various approaches. This work addresses the challenge by proposing a geometry-based approach, leveraging the sequential structure of LiDAR sensors, which sets it apart from the learning-based methods commonly found in the literature. The proposed method, called 3DLabelProp, is applied on the task of LiDAR Semantic Segmentation (LSS). Through extensive experimentation on seven datasets, it is demonstrated to be a state-of-the-art approach, outperforming both naive and other domain generalization methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。