Abstract
This paper revisits few-shot 3D point cloud semantic segmentation (FS-PCS), with a focus on two significant issues in the state-of-the-art: foreground leakage and sparse point distribution. The former arises from non-uniform point sampling, allowing models to distinguish the density disparities between foreground and background for easier segmentation. The latter results from sampling only 2,048 points, limiting semantic information and deviating from the real-world practice. To address these issues, we introduce a standardized FS-PCS setting, upon which a new benchmark is built. Moreover, we propose a novel FS-PCS model. While previous methods are based on feature optimization by mainly refining support features to enhance prototypes, our method is based on correlation optimization, referred to as Correlation Optimization Segmentation (COSeg). Specifically, we compute Class-specific Multi-prototypical Correlation (CMC) for each query point, representing its correlations to category prototypes. Then, we propose the Hyper Correlation Augmentation (HCA) module to enhance CMC. Furthermore, tackling the inherent property of few-shot training to incur base susceptibility for models, we propose to learn non-parametric prototypes for the base classes during training. The learned base prototypes are used to calibrate correlations for the background class through a Base Prototypes Calibration (BPC) module. Experiments on popular datasets demonstrate the superiority of COSeg over existing methods. The code is available at: this https URL
Abstract (translated)
本文回顾了少样本3D点云语义分割（FS-PCS），重点关注了目前最先进的两个重要问题：前景泄漏和稀疏点分布。前者是由于非均匀点采样导致的，使得模型能够更容易地分割出前景和背景之间的密度差异。后者是因为只采样了2,048个点，限制了语义信息，并远离了现实世界的实践。为了应对这些问题，我们引入了一个标准的FS-PCS设置，在此基础上构建了一个新的基准。此外，我们提出了一个新颖的FS-PCS模型。虽然以前的方法是基于主要通过优化支持特征来增强原型，但我们的方法基于相关优化，被称为相关优化分割（COSeg）。具体来说，我们计算每个查询点的类特异性多原型相关（CMC），代表其与类别原型之间的相关性。然后，我们提出了Hyper Correlation Augmentation（HCA）模块来增强CMC。此外，为了解决少样本训练固有的特性，我们提出在训练过程中学习基础类别的非参数原型。通过BPC模块校准背景类的相关，学习到的基础原型被用于通过该模块进行背景类别的相关校准。在流行数据集上的实验证明，COSeg相对于现有方法具有优越性。代码可在此处下载：https://this URL
URL
https://arxiv.org/abs/2403.00592
