PanDA：面向自动驾驶多模态3D全景分割的无监督域自适应
PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving
针对多模态3D全景分割的无监督域自适应框架，其非对称多模态增强和双专家伪标签精炼模块可迁移到其他多模态感知任务（如3D检测、语义分割）的域自适应中，提升传感器退化下的鲁棒性。
原文依据 we propose PanDA, the first UDA framework specifically designed for multimodal 3D panoptic segmentation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文首次研究了多模态3D全景分割（mm-3DPS）的无监督域自适应（UDA），旨在提升在真实自动驾驶场景中常见的域偏移下的泛化能力。一种直接的解决方案是采用伪标签策略，该策略在UDA中广泛用于为无标签目标数据生成监督信号，并结合mm-3DPS骨干网络。然而，现有的监督式mm-3DPS方法严重依赖激光雷达与RGB输入之间的强跨模态互补性，这使得它们在某一模态退化（例如光照不足或恶劣天气）的域偏移下变得脆弱。此外，传统伪标签通常仅保留高置信度区域，导致掩码碎片化和目标监督不完整，这些问题对全景分割尤为不利。为应对这些挑战，我们提出了PanDA，这是首个专为多模态3D全景分割设计的UDA框架。为提升对单传感器退化的鲁棒性，我们引入了一种非对称多模态增强，通过选择性丢弃区域来模拟域偏移并改进鲁棒表征学习。为增强伪标签的完整性和可靠性，我们进一步开发了一个双专家伪标签精炼模块，从2D和3D模态中提取域不变先验。在涵盖时间、天气、地点和传感器变化等多种域偏移上的大量实验显著超越了3D语义分割的最优UDA基线。
英文原文摘要 1593 字符
This paper presents the first study on Unsupervised Domain Adaptation (UDA) for multimodal 3D panoptic segmentation (mm-3DPS), aiming to improve generalization under domain shifts commonly encountered in real-world autonomous driving. A straightforward solution is to employ a pseudo-labeling strategy, which is widely used in UDA to generate supervision for unlabeled target data, combined with an mm-3DPS backbone. However, existing supervised mm-3DPS methods rely heavily on strong cross-modal complementarity between LiDAR and RGB inputs, making them fragile under domain shifts where one modality degrades (e.g., poor lighting or adverse weather). Moreover, conventional pseudo-labeling typically retains only high-confidence regions, leading to fragmented masks and incomplete object supervision, which are issues particularly detrimental to panoptic segmentation. To address these challenges, we propose PanDA, the first UDA framework specifically designed for multimodal 3D panoptic segmentation. To improve robustness against single-sensor degradation, we introduce an asymmetric multimodal augmentation that selectively drops regions to simulate domain shifts and improve robust representation learning. To enhance pseudo-label completeness and reliability, we further develop a dual-expert pseudo-label refinement module that extracts domain-invariant priors from both 2D and 3D modalities. Extensive experiments across diverse domain shifts, spanning time, weather, location, and sensor variations, significantly surpass state-of-the-art UDA baselines for 3D semantic segmentation.