Few Shot 3D Point Cloud Classification On 2
Metrics
Overall Accuracy
Standard Deviation
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Overall Accuracy | Standard Deviation |
|---|---|---|
| point2vec-for-self-supervised-representation | 98.7 | 1.2 |
| point-jepa-a-joint-embedding-predictive | 99.2 | 0.8 |
| pre-training-by-completing-point-clouds | 92.4 | 1.6 |
| instance-aware-dynamic-prompt-tuning-for-pre | 97.9 | - |
| pointnet-deep-hierarchical-feature-learning | 42.39 | 14.2 |
| pcp-mae-learning-to-predict-centers-for-point | 99.1 | 0.8 |
| pointcnn-convolution-on-x-transformed-points | 68.64 | 7.0 |
| regress-before-construct-regress-autoencoder | 98.7 | 1.3 |
| autoencoders-as-cross-modal-teachers-can | 98.0 | 1.4 |
| gpr-net-geometric-prototypical-network-for | 82.0 | 0.9 |
| gpr-net-geometric-prototypical-network-for | 82.7 | 1.3 |
| pointnet-deep-learning-on-point-sets-for-3d | 57.81 | 15.5 |
| point-lgmask-local-and-global-contexts | 98.1 | 1.4 |
| masked-autoencoders-for-point-cloud-self | 97.8 | 1.8 |
| pre-training-by-completing-point-clouds | 92.5 | 1.9 |
| 3d-jepa-a-joint-embedding-predictive | 98.8 | 0.4 |
| masked-discrimination-for-self-supervised | 97.2 | 1.7 |
| self-supervised-few-shot-learning-on-point | 68.90 | 9.4 |
| dynamic-graph-cnn-for-learning-on-point | 40.8 | 14.6 |
| gpr-net-geometric-prototypical-network-for | 75.1 | 2.1 |
| contrast-with-reconstruct-contrastive-3d | 98.9 | 1.2 |
| self-supervised-few-shot-learning-on-point | 65.70 | 8.4 |
| gpr-net-geometric-prototypical-network-for | 75.0 | 2.4 |
| point-m2ae-multi-scale-masked-autoencoders | 98.3 | 1.4 |
| rethinking-masked-representation-learning-for | 98.7 | 1.2 |
| shapellm-universal-3d-object-understanding | 99.5 | 0.8 |
| pointgpt-auto-regressively-generative-pre-1 | 99.0 | 1.0 |
| point-bert-pre-training-3d-point-cloud | 96.3 | 2.7 |
| crossmoco-multi-modal-momentum-contrastive | 96.8 | 1.7 |
| learning-3d-representations-from-2d-pre | 98.3 | 1.3 |