Masked autoencoding has become a successful pretraining paradigm for Transformer models for text, images, and, recently, point clouds. Raw automotive datasets are suitable candidates for self-supervised pre-training as they generally are cheap to collect compared to annotations for tasks like 3D object detection (OD). However, the development of masked autoencoders for point clouds has focused solely on synthetic and indoor data. Consequently, existing methods have tailored their representations and models toward small and dense point clouds with homogeneous point densities. In this work, we study masked autoencoding for point clouds in an automotive setting, which are sparse and for which the point density can vary drastically among objects in the same scene. To this end, we propose Voxel-MAE, a simple masked autoencoding pre-training scheme designed for voxel representations. We pre-train the backbone of a Transformer-based 3D object detector to reconstruct masked voxels and to distinguish between empty and non-empty voxels. Our method improves the 3D OD performance by 1.75 mAP points and 1.05 NDS on the challenging nuScenes dataset. Further, we show that by pre-training with Voxel-MAE, we require only 40% of the annotated data to outperform a randomly initialized equivalent. Code available at https://github.com/georghess/voxel-mae
翻译:保护自动自动编码器已经成为一个成功的文本、图像和最近点云的变换模型培训前范例。 原始汽车数据集是适合自行监督预培训的合适人选, 因为与3D对象探测(OD)等任务的说明相比,它们一般是廉价的,可以收集。 然而, 用于点云的蒙面自动编码器的开发完全侧重于合成和室内数据。 因此, 现有方法已经将其表示和模型调整为具有同质点密度的小型和稠密点云。 在这项工作中, 我们研究汽车环境下点云的蒙面自动编码, 这些云十分稀少, 在同一场景的物体中点密度可能有很大差异。 为此, 我们提议为 voxel- 对象探测( ODAE) 设计一个简单的蒙面自动编码前训练程序。 我们预先将基于3D 对象的变压器探测器的骨架放在骨架上, 以重建掩码的 voxelson 并区分空和非空的 voxelsells。 我们的方法将3DOD的功能改进为1. 75 mAP 和1.05 NDS- train of data- exstrainment of exstrualse ex ex ex ex exupdustrain a ex. weredustrabildown.</s>