Few Shot 3D Point Cloud Classification On 4
평가 지표
Overall Accuracy
Standard Deviation
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Overall Accuracy | Standard Deviation |
|---|---|---|
| point-lgmask-local-and-global-contexts | 95.1 | 3.4 |
| self-supervised-few-shot-learning-on-point | 50.10 | 5.0 |
| autoencoders-as-cross-modal-teachers-can | 95.6 | 2.8 |
| pointgpt-auto-regressively-generative-pre-1 | 96.1 | 2.8 |
| masked-autoencoders-for-point-cloud-self | 95.0 | 3.0 |
| gpr-net-geometric-prototypical-network-for | 73.8 | 2.0 |
| crossmoco-multi-modal-momentum-contrastive | 91.0 | 3.4 |
| gpr-net-geometric-prototypical-network-for | 63.3 | 2.2 |
| pcp-mae-learning-to-predict-centers-for-point | 95.9 | 2.7 |
| rethinking-masked-representation-learning-for | 95.6 | 2.6 |
| shapellm-universal-3d-object-understanding | 96.5 | 3.0 |
| pointnet-deep-learning-on-point-sets-for-3d | 35.20 | 13.5 |
| pointnet-deep-hierarchical-feature-learning | 18.80 | 7.0 |
| pointcnn-convolution-on-x-transformed-points | 49.95 | 7.2 |
| gpr-net-geometric-prototypical-network-for | 63.4 | 2.0 |
| dynamic-graph-cnn-for-learning-on-point | 16.9 | 1.5 |
| regress-before-construct-regress-autoencoder | 95.8 | 3.0 |
| pre-training-by-completing-point-clouds | 89.7 | 1.5 |
| point-m2ae-multi-scale-masked-autoencoders | 95.0 | 3.0 |
| instance-aware-dynamic-prompt-tuning-for-pre | 95.4 | - |
| masked-discrimination-for-self-supervised | 93.4 | 3.5 |
| gpr-net-geometric-prototypical-network-for | 72.8 | 1.8 |
| towards-compact-3d-representations-via-point | 95.8 | - |
| 3d-jepa-a-joint-embedding-predictive | 96.3 | 2.4 |
| contrast-with-reconstruct-contrastive-3d | 95.8 | 3.0 |
| pre-training-by-completing-point-clouds | 86.5 | 2.2 |
| point-bert-pre-training-3d-point-cloud | 92.7 | 5.1 |
| point-jepa-a-joint-embedding-predictive | 96.4 | 2.7 |
| self-supervised-few-shot-learning-on-point | 53.00 | 4.1 |
| point2vec-for-self-supervised-representation | 95.8 | 3.1 |
| learning-3d-representations-from-2d-pre | 95.5 | 3.0 |