Let θ and φ denote the optimal parameters after model training. The detailed statistics of three datasets used in this paper are listed in Table 1. In this paper, when evaluating the performance in the standard experimental scenario and in the label-scarce scenario, we compare with six state-of-the-art baselines used for graph-based semisupervised learning. Three of them are deterministic GNN-based models, which are GCN [1], Graph Attention Networks(GAT)[2]andGraphSAGE[3]respectively.

Wefirst implement global augmentation approaches including random rotation and random scaling on two LiDAR scans separately and thenconcatenate themfortraining. The more copies the better segmentation performance as shown in ' 1, 2, 3' in the table, which indicates the effectiveness of the approach in enriching data distribution. In this section, we conducted experiments to analyze how PolarMix benefits LiDAR point cloud learning. As a comparison, PolarMix is more robust to the instance spatial location without much performance drop. PolarMix improves the robustness of the baseline clearly with respect to the angular variations of instances (i.e.

Wecompare our reimplementation against the original numbers reported in the paper on the original Shape2Motion dataset.

Table A: Configuration of the main parameters used for executing each episode of the PIN task containedinthePInNEDdataset.

We expect that this should be the case, since neural networks are often good at memorizing rare examples.