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/Swin3D-L

Swin3D-L

Reported on 16 benchmarks across 2 tasks · 1 paper · 14 SOTA

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

Medical8 results

Semantic SegmentationonScanNet
val mIoU· uses extra data· 2023-04-14
77.5
best: 80.5 (DITR)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
Semantic SegmentationonS3DIS Area5
mAcc· uses extra data· 2023-04-14
80.5
best: 81.6 (Sonata + PTv3)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
Semantic SegmentationonS3DIS Area5
mIoU· uses extra data· 2023-04-14
74.5
best: 76 (Sonata + PTv3)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
Semantic SegmentationonS3DIS Area5
oAcc· uses extra data· 2023-04-14
92.7
best: 93 (Sonata + PTv3)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
Semantic SegmentationonS3DIS
Mean IoU· uses extra data· 2023-04-14
79.8
best: 82.3 (Sonata + PTv3)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
Semantic SegmentationonS3DIS
mAcc· uses extra data· 2023-04-14
88
best: 89.9 (Sonata + PTv3)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
Semantic SegmentationonS3DIS
oAcc· uses extra data· 2023-04-14
92.4
best: 93.3 (Sonata + PTv3)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
Semantic SegmentationonScanNet
test mIoU· uses extra data· 2023-04-14
77.9
best: 79.8 (PTv3 ARKit LabelMaker)
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906

Audio8 results

10-shot image generationonScanNet
val mIoU· uses extra data· 2023-04-14
77.5
best: 80.5 (DITR)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
10-shot image generationonS3DIS Area5
mAcc· uses extra data· 2023-04-14
80.5
best: 81.6 (Sonata + PTv3)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
10-shot image generationonS3DIS Area5
mIoU· uses extra data· 2023-04-14
74.5
best: 76 (Sonata + PTv3)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
10-shot image generationonS3DIS Area5
oAcc· uses extra data· 2023-04-14
92.7
best: 93 (Sonata + PTv3)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
10-shot image generationonS3DIS
Mean IoU· uses extra data· 2023-04-14
79.8
best: 82.3 (Sonata + PTv3)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
10-shot image generationonS3DIS
mAcc· uses extra data· 2023-04-14
88
best: 89.9 (Sonata + PTv3)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
10-shot image generationonS3DIS
oAcc· uses extra data· 2023-04-14
92.4
best: 93.3 (Sonata + PTv3)
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
10-shot image generationonScanNet
test mIoU· uses extra data· 2023-04-14
77.9
best: 79.8 (PTv3 ARKit LabelMaker)
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906