论文标题
少数射击3D点云语义分段
Few-shot 3D Point Cloud Semantic Segmentation
论文作者
论文摘要
3D点云语义细分的许多现有方法都是完全监督的。这些全面监督的方法在很大程度上依赖大量的标记培训数据，这些数据很难获得，并且在培训后无法细分新课程。为了减轻这些局限性，我们提出了一种新型的注意力吸引人的多型转型型频点云语义分割方法，以分割新类，并给出一些标记的示例。具体而言，每个类都由多个原型表示，以建模标记点的复杂数据分布。随后，我们采用偏置标签传播方法来利用标记的多型型和未标记点之间以及未标记的点之间的亲和力。此外，我们设计了一个注意力吸引人的多层次特征学习网络，以学习捕获几何依赖性和点之间的语义相关性的判别特征。我们提出的方法在两个基准数据集上的不同少点云语义分割设置（即2/3way 1/5-shot）中的基线显示出显着且一致的改进。我们的代码可在https://github.com/na-z/attmpti上找到。
Many existing approaches for 3D point cloud semantic segmentation are fully supervised. These fully supervised approaches heavily rely on large amounts of labeled training data that are difficult to obtain and cannot segment new classes after training. To mitigate these limitations, we propose a novel attention-aware multi-prototype transductive few-shot point cloud semantic segmentation method to segment new classes given a few labeled examples. Specifically, each class is represented by multiple prototypes to model the complex data distribution of labeled points. Subsequently, we employ a transductive label propagation method to exploit the affinities between labeled multi-prototypes and unlabeled points, and among the unlabeled points. Furthermore, we design an attention-aware multi-level feature learning network to learn the discriminative features that capture the geometric dependencies and semantic correlations between points. Our proposed method shows significant and consistent improvements compared to baselines in different few-shot point cloud semantic segmentation settings (i.e., 2/3-way 1/5-shot) on two benchmark datasets. Our code is available at https://github.com/Na-Z/attMPTI.
