超越标签本身：潜在标签增强半监督点云全景分割
Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation
AI总结：
针对点云半监督全景分割，本文提出Cylinder-Mix增强方法与IPSL模块，通过挖掘LiDAR和图像中的潜在标签信息并嵌入多模态网络，在SemanticKITTI和nuScenes上优于SOTA方法LaserMix。
摘要：
鉴于标注自动驾驶数据集的高昂成本以及利用无标签数据的趋势，点云上的半监督分割变得日益迫切。直观上，找出标签本身之外更多“未言明之意”（即潜在实例信息）应有助于提升性能。本文发现了嵌入LiDAR和图像数据中的显示标签背后的两类潜在标签。首先，在LiDAR分支中，我们提出了一种新颖的增强方法Cylinder-Mix，能够为训练增加更多且可靠的样本。其次，在图像分支中，我们提出了实例位置-尺度学习（IPSL）模块，用于学习并融合实例位置与尺度信息，该信息源自2D预训练检测器以及一种从3D到2D投影获得的潜在标签。最后，这两类潜在标签被嵌入到多模态全景分割网络中。对IPSL模块的消融实验证明了其强大的适应性，在SemanticKITTI和nuScenes上的评估实验表明，我们的模型优于最先进的方法LaserMix。
英文摘要：
As the exorbitant expense of labeling autopilot datasets and the growing trend of utilizing unlabeled data, semi-supervised segmentation on point clouds becomes increasingly imperative. Intuitively, finding out more ``unspoken words'' (i.e., latent instance information) beyond the label itself should be helpful to improve performance. In this paper, we discover two types of latent labels behind the displayed label embedded in LiDAR and image data. First, in the LiDAR Branch, we propose a novel augmentation, Cylinder-Mix, which is able to augment more yet reliable samples for training. Second, in the Image Branch, we propose the Instance Position-scale Learning (IPSL) Module to learn and fuse the information of instance position and scale, which is from a 2D pre-trained detector and a type of latent label obtained from 3D to 2D projection. Finally, the two latent labels are embedded into the multi-modal panoptic segmentation network. The ablation of the IPSL module demonstrates its robust adaptability, and the experiments evaluated on SemanticKITTI and nuScenes demonstrate that our model outperforms the state-of-the-art method, LaserMix.
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。
