Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?

Open paper
Benchmark Model Rank Results
few-shot-3d-point-cloud-classification-on-modelnet40-10-way-10-shotACT#12Overall Accuracy: 93.3Standard Deviation: 4.0
few-shot-3d-point-cloud-classification-on-modelnet40-10-way-20-shotACT#13Overall Accuracy: 95.6Standard Deviation: 2.8
few-shot-3d-point-cloud-classification-on-modelnet40-5-way-10-shotACT#19Overall Accuracy: 96.8Standard Deviation: 2.3
few-shot-3d-point-cloud-classification-on-modelnet40-5-way-20-shotACT#20Overall Accuracy: 98.0Standard Deviation: 1.4
3d-point-cloud-classification-on-scanobjectnnACT#29Overall Accuracy: 89.17
3d-point-cloud-classification-on-scanobjectnnACT (no voting)#37Overall Accuracy: 88.21OBJ-BG (OA): 93.29OBJ-ONLY (OA): 91.91

Rank counts only results with a code link.