UNIT：基于时间序列的无监督在线实例分割
UNIT: Unsupervised Online Instance Segmentation through Time
AI总结：
针对激光雷达点云在线实例分割与追踪人工标注成本高的问题，提出基于伪标签训练的无监督类别无关在线实例分割方法，在两个户外激光雷达数据集上优于强基线。
摘要：
激光雷达点云中的在线目标分割与追踪可让自主智能体理解周边环境并做出安全决策。遗憾的是，这些任务的人工标注成本极高。我们针对类别无关的无监督在线实例分割与追踪任务来解决这一问题。为此，我们采用一个实例分割骨干网络，并提出一种全新的训练方案以实现目标的在线追踪。我们的网络基于伪标签训练，无需人工标注。我们使用适配时序实例分割的指标开展评估，计算这些指标需要时序一致的实例标签；当这类标签不存在时，我们利用数据集中可用的3D边界框和语义标签构建此类标签。我们将所提方法与强基线模型进行对比，在两个不同的户外激光雷达数据集上均证明了其优越性。
英文摘要：
Online object segmentation and tracking in Lidar point clouds enables autonomous agents to understand their surroundings and make safe decisions. Unfortunately, manual annotations for these tasks are prohibitively costly. We tackle this problem with the task of class-agnostic unsupervised online instance segmentation and tracking. To that end, we leverage an instance segmentation backbone and propose a new training recipe that enables the online tracking of objects. Our network is trained on pseudo-labels, eliminating the need for manual annotations. We conduct an evaluation using metrics adapted for temporal instance segmentation. Computing these metrics requires temporally-consistent instance labels. When unavailable, we construct these labels using the available 3D bounding boxes and semantic labels in the dataset. We compare our method against strong baselines and demonstrate its superiority across two different outdoor Lidar datasets.
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。
