论文标题
宇宙：3D激光雷达分割中域适应的组成语义混合
CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation
论文作者
论文摘要
3D激光雷达语义细分对于自动驾驶是基础。最近已经提出了几种用于点云数据的无监督域适应性（UDA）方法，以改善不同传感器和环境的模型概括。研究图像域中研究UDA问题的研究人员表明，样品混合可以减轻域的转移。我们提出了一种针对点云UDA的样品混合的新方法，即组成语义混合（Cosmix），这是基于样品混合的点云分割的第一种UDA方法。 Cosmix由一个两分支对称网络组成，该网络可以同时处理标记的合成数据（源）和现实世界中未标记的点云（目标）。每个分支通过将选定的数据从另一个域进行混合，并使用来自源标签和目标伪标签的语义信息来在一个域上运行。我们在两个大规模数据集上评估Cosmix，这表明它的表现要优于最先进的方法。我们的代码可在https://github.com/saltoricristiano/cosmix-uda上找到。
3D LiDAR semantic segmentation is fundamental for autonomous driving. Several Unsupervised Domain Adaptation (UDA) methods for point cloud data have been recently proposed to improve model generalization for different sensors and environments. Researchers working on UDA problems in the image domain have shown that sample mixing can mitigate domain shift. We propose a new approach of sample mixing for point cloud UDA, namely Compositional Semantic Mix (CoSMix), the first UDA approach for point cloud segmentation based on sample mixing. CoSMix consists of a two-branch symmetric network that can process labelled synthetic data (source) and real-world unlabelled point clouds (target) concurrently. Each branch operates on one domain by mixing selected pieces of data from the other one, and by using the semantic information derived from source labels and target pseudo-labels. We evaluate CoSMix on two large-scale datasets, showing that it outperforms state-of-the-art methods by a large margin. Our code is available at https://github.com/saltoricristiano/cosmix-uda.
