Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Point-JEPA

Point-JEPA

Reported on 31 benchmarks across 5 tasks · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision27 results

Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2024-04-25
95
SOTA
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2024-04-25
95
SOTA
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2024-04-25
95
SOTA
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy· uses extra data· 2024-04-25
86.6
best: 97.2 (OmniVec2)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2024-04-25
96.4
best: 96.5 (ReCon++)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2024-04-25
2.7
best: 13.5 (PointNet)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2024-04-25
97.4
best: 98 (PointGPT)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2024-04-25
2.2
best: 16 (PointNet++)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2024-04-25
3.6
best: 13.5 (PointNet)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2024-04-25
99.2
best: 99.5 (ReCon++)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2024-04-25
0.8
best: 15.5 (PointNet)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy· uses extra data· 2024-04-25
86.6
best: 97.2 (OmniVec2)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2024-04-25
96.4
best: 96.5 (ReCon++)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2024-04-25
2.7
best: 13.5 (PointNet)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2024-04-25
97.4
best: 98 (PointGPT)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2024-04-25
2.2
best: 16 (PointNet++)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2024-04-25
3.6
best: 13.5 (PointNet)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2024-04-25
99.2
best: 99.5 (ReCon++)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2024-04-25
0.8
best: 15.5 (PointNet)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy· uses extra data· 2024-04-25
86.6
best: 97.2 (OmniVec2)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2024-04-25
96.4
best: 96.5 (ReCon++)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2024-04-25
2.7
best: 13.5 (PointNet)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2024-04-25
97.4
best: 98 (PointGPT)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2024-04-25
2.2
best: 16 (PointNet++)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2024-04-25
3.6
best: 13.5 (PointNet)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2024-04-25
99.2
best: 99.5 (ReCon++)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2024-04-25
0.8
best: 15.5 (PointNet)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432

Medical2 results

Semantic SegmentationonShapeNet-Part
Class Average IoU· uses extra data· 2024-04-25
85.8
best: 87.7 (Feature Geometric Net (FG-Net))
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
Semantic SegmentationonShapeNet-Part
Instance Average IoU· uses extra data· 2024-04-25
83.9
best: 89.1 (GeomGCNN)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432

Audio2 results

10-shot image generationonShapeNet-Part
Class Average IoU· uses extra data· 2024-04-25
85.8
best: 87.7 (Feature Geometric Net (FG-Net))
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432
10-shot image generationonShapeNet-Part
Instance Average IoU· uses extra data· 2024-04-25
83.9
best: 89.1 (GeomGCNN)
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud arXiv:2404.16432