通过多模型协作学习，提升点云语义分割在少量标注数据下的性能。
Collaborative Learning for Semi-Supervised LiDAR Semantic Segmentation
- 多个模型协同训练，动态融合彼此的预测作为伪标签。
- 在三个数据集上均超越现有方法，低标注率下提升显著。
- 适合需要高效利用少量标注数据的3D感知任务研究者。
大规模激光雷达点云的3D语义分割标注成本高昂，推动了半监督学习（SemiSL）的应用。现有方法通常采用两阶段训练范式，从单一来源生成伪标签，易受确认偏差影响并传播错误，限制性能。为此，本文提出CoLLiS框架，采用协作学习机制，在单步训练中让多个表示作为平等学生协同优化。每个学生从多个表示中自适应地进行知识蒸馏，同时在线监控学生间差异，以解决矛盾监督并有效缓解确认偏差。在三个数据集上的大量实验表明，CoLLiS持续优于当前最优的激光雷达半监督方法，尤其在低标注率条件下表现突出。
原文摘要 · Abstract (English)
Annotating large-scale LiDAR point clouds for 3D semantic segmentation is costly and time-consuming, which motivates the use of semi-supervised learning (SemiSL). Standard LiDAR SemiSL methods typically adopt a two-step training paradigm, where pseudo-labels are separately generated from a single distillation source, either from the same or another LiDAR representation. Such supervision relies on a unique source of pseudo-labels, which can reinforce confirmation bias and propagate errors during training, ultimately limiting performance. To address this challenge, we introduce CoLLiS, a novel framework that leverages Collaborative Learning for LiDAR Semi-supervised segmentation. Unlike prior paradigms with decoupled pseudo-labeling and training phases, CoLLiS trains multiple representations collaboratively in a single step by treating them as coequal students. Each student is adaptively distilled from multiple representations, while inter-student disparities are monitored online to resolve contradictory supervision and effectively mitigate confirmation bias. Extensive experiments on three datasets demonstrate that CoLLiS consistently outperforms state-of-the-art LiDAR SemiSL methods, with particularly strong gains in low-label regimes.
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。