Multiscale Receptive Fields Graph Attention Network for Point Cloud Classification

Table 1

Classification results on ModelNet40. MA represents mean per-class accuracy, and the per-class accuracy is the ratio of the number of correct classifications to that of the objects in a class. OA denotes the overall accuracy, which is the ratio of the number of overall correct classifications to that of overall objects.

Method	Points	MA (%)	OA (%)
SO-Net [38]	20483	87.3	90.9
KD-Net [40]	10243	88.5	91.8
PointNet [19]	10243	86.0	89.2
PointNet++ [20]	10243	—	90.7
PointCNN [21]	10243	88.1	92.2
DGCNN [26]	10243	90.2	92.2
PCNN [22]	10243	—	92.3
GAPNet [34]	10243	89.7	92.4
Ours	10243	90.1	92.5