论文标题
SALA：软件局部聚合，用于参数有效3D语义分割
SALA: Soft Assignment Local Aggregation for Parameter Efficient 3D Semantic Segmentation
论文作者
论文摘要
在这项工作中，我们专注于设计一个局部聚合函数，该功能可为3D点云语义分割产生参数有效网络。我们探索在基于网格的聚合功能中使用可学习的邻居到网格软分配的想法。文献中先前的方法在预定义的几何网格（例如局部体积分区或不规则的内核点）上运行。更一般的替代方法是允许网络学习最适合最终任务的分配功能。由于它是可以学习的，因此允许将此映射不同，而不是在整个网络的深度中均匀地应用。通过赋予网络以学习自己的邻居到网格分配的灵活性，我们获得了参数有效的模型，这些模型与当前重新签名方法相比，具有至少10 $ \ times $少于10 $ \ times $的参数。与更大的SOTA模型相比，我们还展示了扫描仪和part网的竞争性能。
In this work, we focus on designing a point local aggregation function that yields parameter efficient networks for 3D point cloud semantic segmentation. We explore the idea of using learnable neighbor-to-grid soft assignment in grid-based aggregation functions. Previous methods in literature operate on a predefined geometric grid such as local volume partitions or irregular kernel points. A more general alternative is to allow the network to learn an assignment function that best suits the end task. Since it is learnable, this mapping is allowed to be different per layer instead of being applied uniformly throughout the depth of the network. By endowing the network with the flexibility to learn its own neighbor-to-grid assignment, we arrive at parameter efficient models that achieve state-of-the-art (SOTA) performance on S3DIS with at least 10$\times$ less parameters than the current reigning method. We also demonstrate competitive performance on ScanNet and PartNet compared with much larger SOTA models.
