Few Shot 3D Point Cloud Classification On 3
평가 지표
Overall Accuracy
Standard Deviation
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Overall Accuracy | Standard Deviation |
|---|---|---|
| pcp-mae-learning-to-predict-centers-for-point | 93.5 | 3.7 |
| gpr-net-geometric-prototypical-network-for | 62.1 | 1.9 |
| point-bert-pre-training-3d-point-cloud | 91.0 | 5.4 |
| masked-discrimination-for-self-supervised | 91.4 | 4.0 |
| dynamic-graph-cnn-for-learning-on-point | 19.85 | 6.5 |
| point-m2ae-multi-scale-masked-autoencoders | 92.3 | 4.5 |
| gpr-net-geometric-prototypical-network-for | 70.4 | 1.8 |
| instance-aware-dynamic-prompt-tuning-for-pre | 92.8 | - |
| pointnet-deep-learning-on-point-sets-for-3d | 46.60 | 13.5 |
| regress-before-construct-regress-autoencoder | 93.3 | 4.0 |
| point-lgmask-local-and-global-contexts | 92.6 | 4.3 |
| shapellm-universal-3d-object-understanding | 94.5 | 4.1 |
| gpr-net-geometric-prototypical-network-for | 62.3 | 2.0 |
| masked-autoencoders-for-point-cloud-self | 92.6 | 4.1 |
| pointcnn-convolution-on-x-transformed-points | 46.60 | 4.8 |
| 3d-jepa-a-joint-embedding-predictive | 94.3 | 3.6 |
| pointgpt-auto-regressively-generative-pre-1 | 94.3 | 3.3 |
| pre-training-by-completing-point-clouds | 82.9 | 1.3 |
| pointnet-deep-hierarchical-feature-learning | 23.05 | 7.0 |
| towards-compact-3d-representations-via-point | 94.0 | - |
| self-supervised-few-shot-learning-on-point | 49.15 | 6.1 |
| point-jepa-a-joint-embedding-predictive | 95.0 | 3.6 |
| contrast-with-reconstruct-contrastive-3d | 93.3 | 3.9 |
| autoencoders-as-cross-modal-teachers-can | 93.3 | 4.0 |
| rethinking-masked-representation-learning-for | 93.2 | 3.4 |
| self-supervised-few-shot-learning-on-point | 48.50 | 5.6 |
| learning-3d-representations-from-2d-pre | 92.6 | 5.0 |
| pre-training-by-completing-point-clouds | 83.9 | 1.8 |
| point2vec-for-self-supervised-representation | 93.9 | 4.1 |
| gpr-net-geometric-prototypical-network-for | 71.6 | 1.1 |
| crossmoco-multi-modal-momentum-contrastive | 88.7 | 3.9 |