PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders

Open paper
Benchmark Model Rank Results
few-shot-3d-point-cloud-classification-on-modelnet40-5-way-20-shotPCP-MAE#4Overall Accuracy: 99.1Standard Deviation: 0.8
few-shot-3d-point-cloud-classification-on-modelnet40-10-way-20-shotPCP-MAE#6Overall Accuracy: 95.9Standard Deviation: 2.7
few-shot-3d-point-cloud-classification-on-modelnet40-5-way-10-shotPCP-MAE#7Overall Accuracy: 97.4Standard Deviation: 2.3
few-shot-3d-point-cloud-classification-on-modelnet40-10-way-10-shotPCP-MAE#10Overall Accuracy: 93.5Standard Deviation: 3.7
3d-point-cloud-classification-on-scanobjectnnPCP-MAE#15Overall Accuracy: 90.35OBJ-BG (OA): 95.52OBJ-ONLY (OA): 94.32
3d-point-cloud-classification-on-modelnet40PCP-MAE#21Overall Accuracy: 94.2

Rank counts only results with a code link.