用于三维目标检测的图神经网络动态边缘权值
Dynamic Edge Weights in Graph Neural Networks for 3D Object Detection
摘要：
强大而精确的3D检测系统是自动驾驶汽车不可或缺的一部分。传统上，大多数3D目标检测算法集中于使用体素网格或鸟瞰图（BEV）来处理3D点云。然而，最近的工作表明，利用图神经网络（GNN）作为一个有前途的方法，三维目标检测。在这项工作中，我们提出了一个基于注意力的特征聚合技术在GNN检测激光雷达扫描中的对象。我们首先采用了一个距离感知下采样方案，不仅提高了算法的性能，但也保留了最大的几何特征的对象，即使他们远离传感器。在GNN的每一层中，除了将每节点输入特征映射到对应的更高级别特征的线性变换之外，还执行通过向其第一环邻域中的不同节点指定不同权重的每节点掩蔽注意力。掩蔽注意力隐式地考虑了每个节点的底层邻域图结构，并且还消除了昂贵的矩阵运算的需要，从而在不损害性能的情况下提高了检测精度。在KITTI数据集上的实验表明，该方法在三维目标检测中具有较好的效果。
英文摘要：
A robust and accurate 3D detection system is an integral part of autonomous vehicles. Traditionally, a majority of 3D object detection algorithms focus on processing 3D point clouds using voxel grids or bird's eye view (BEV). Recent works, however, demonstrate the utilization of the graph neural network (GNN) as a promising approach to 3D object detection. In this work, we propose an attention based feature aggregation technique in GNN for detecting objects in LiDAR scan. We first employ a distance-aware down-sampling scheme that not only enhances the algorithmic performance but also retains maximum geometric features of objects even if they lie far from the sensor. In each layer of the GNN, apart from the linear transformation which maps the per node input features to the corresponding higher level features, a per node masked attention by specifying different weights to different nodes in its first ring neighborhood is also performed. The masked attention implicitly accounts for the underlying neighborhood graph structure of every node and also eliminates the need of costly matrix operations thereby improving the detection accuracy without compromising the performance. The experiments on KITTI dataset show that our method yields comparable results for 3D object detection.
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。
