Positional Prompt Tuning for Efficient 3D Representation Learning

Open paper
Benchmark Model Rank Results
3d-point-cloud-classification-on-scanobjectnnReCon+PPT#23Overall Accuracy: 89.52OBJ-BG (OA): 95.01OBJ-ONLY (OA): 93.28
3d-point-cloud-classification-on-modelnet40PointMAE+PPT#37Overall Accuracy: 93.88

Rank counts only results with a code link.