Few Shot 3D Point Cloud Classification On 1
Métriques
Overall Accuracy
Standard Deviation
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Overall Accuracy | Standard Deviation |
|---|---|---|
| pcp-mae-learning-to-predict-centers-for-point | 97.4 | 2.3 |
| dynamic-graph-cnn-for-learning-on-point | 31.6 | 9.0 |
| learning-3d-representations-from-2d-pre | 97.0 | 1.8 |
| shapellm-universal-3d-object-understanding | 98.0 | 2.3 |
| masked-discrimination-for-self-supervised | 95.0 | 3.7 |
| gpr-net-geometric-prototypical-network-for | 74.4 | 2.0 |
| masked-autoencoders-for-point-cloud-self | 96.3 | 2.5 |
| pointgpt-auto-regressively-generative-pre-1 | 98.0 | 1.9 |
| contrast-with-reconstruct-contrastive-3d | 97.3 | 1.9 |
| autoencoders-as-cross-modal-teachers-can | 96.8 | 2.3 |
| pointnet-deep-hierarchical-feature-learning | 38.53 | 16.0 |
| point-m2ae-multi-scale-masked-autoencoders | 96.8 | 1.8 |
| pre-training-by-completing-point-clouds | 90.6 | 2.8 |
| pre-training-by-completing-point-clouds | 89.7 | 1.9 |
| pointcnn-convolution-on-mathcalx-transformed | 65.41 | 8.9 |
| self-supervised-few-shot-learning-on-point | 63.2 | 10.7 |
| gpr-net-geometric-prototypical-network-for | 81.1 | 1.5 |
| point-jepa-a-joint-embedding-predictive | 97.4 | 2.2 |
| gpr-net-geometric-prototypical-network-for | 80.4 | 0.5 |
| point-bert-pre-training-3d-point-cloud | 94.6 | 3.1 |
| self-supervised-few-shot-learning-on-point | 60.0 | 8.9 |
| pointnet-deep-learning-on-point-sets-for-3d | 51.97 | 12.1 |
| point2vec-for-self-supervised-representation | 97.0 | 2.8 |
| crossmoco-multi-modal-momentum-contrastive | 93.8 | 4.5 |
| 3d-jepa-a-joint-embedding-predictive | 97.6 | 2.0 |
| regress-before-construct-regress-autoencoder | 97.3 | 1.6 |
| point-lgmask-local-and-global-contexts | 97.4 | 2.0 |
| rethinking-masked-representation-learning-for | 97.2 | 2.3 |
| instance-aware-dynamic-prompt-tuning-for-pre | 97.3 | - |
| gpr-net-geometric-prototypical-network-for | 74.0 | 2.3 |