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/Sonata + PTv3

Sonata + PTv3

Reported on 17 benchmarks across 3 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· 2025-03-20
79.4
best: 80.5 (DITR)
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
Semantic SegmentationonS3DIS Area5
mAcc· uses extra data· 2025-03-20
81.6
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
Semantic SegmentationonS3DIS Area5
mIoU· uses extra data· 2025-03-20
76
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
Semantic SegmentationonS3DIS Area5
oAcc· uses extra data· 2025-03-20
93
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
Semantic SegmentationonS3DIS
Mean IoU· uses extra data· 2025-03-20
82.3
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
Semantic SegmentationonS3DIS
mAcc· uses extra data· 2025-03-20
89.9
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
Semantic SegmentationonS3DIS
oAcc· uses extra data· 2025-03-20
93.3
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
Semantic SegmentationonScanNet200
val mIoU· uses extra data· 2025-03-20
36.8
best: 41.2 (DITR)
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429

Audio8 results

10-shot image generationonScanNet
val mIoU· uses extra data· 2025-03-20
79.4
best: 80.5 (DITR)
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
10-shot image generationonS3DIS Area5
mAcc· uses extra data· 2025-03-20
81.6
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
10-shot image generationonS3DIS Area5
mIoU· uses extra data· 2025-03-20
76
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
10-shot image generationonS3DIS Area5
oAcc· uses extra data· 2025-03-20
93
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
10-shot image generationonS3DIS
Mean IoU· uses extra data· 2025-03-20
82.3
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
10-shot image generationonS3DIS
mAcc· uses extra data· 2025-03-20
89.9
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
10-shot image generationonS3DIS
oAcc· uses extra data· 2025-03-20
93.3
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
10-shot image generationonScanNet200
val mIoU· uses extra data· 2025-03-20
36.8
best: 41.2 (DITR)
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429

Computer Vision1 result

3D Semantic SegmentationonScanNet200
val mIoU· uses extra data· 2025-03-20
36.8
best: 41.2 (DITR)
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429