CrossJEPA: Cross-Modal Joint-Embedding Predictive Architecture for Efficient 3D Representation Learning from 2D Images

Benchmark Model Rank Results
few-shot-3d-point-cloud-classification-on-modelnet40-10-way-10-shotCrossJEPA–Overall Accuracy: 95.0
few-shot-3d-point-cloud-classification-on-modelnet40-10-way-20-shotCrossJEPA–Overall Accuracy: 96.5
few-shot-3d-point-cloud-classification-on-modelnet40-5-way-10-shotCrossJEPA–Overall Accuracy: 97.8
few-shot-3d-point-cloud-classification-on-modelnet40-5-way-20-shotCrossJEPA–Overall Accuracy: 99.0