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

Sonata

Reported on 6 benchmarks across 3 tasks · 1 paper · 6 SOTA

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

Medical2 results

Semantic SegmentationonScanNet++
Top-1 IoU· uses extra data· 2025-03-20
0.495
best: 0.525 (DITR)
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
Semantic SegmentationonScanNet++
Top-3 IoU· uses extra data· 2025-03-20
0.735
best: 0.762 (DITR)
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429

Computer Vision2 results

3D Semantic SegmentationonScanNet++
Top-1 IoU· uses extra data· 2025-03-20
0.495
best: 0.525 (DITR)
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
3D Semantic SegmentationonScanNet++
Top-3 IoU· uses extra data· 2025-03-20
0.735
best: 0.762 (DITR)
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429

Audio2 results

10-shot image generationonScanNet++
Top-1 IoU· uses extra data· 2025-03-20
0.495
best: 0.525 (DITR)
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429
10-shot image generationonScanNet++
Top-3 IoU· uses extra data· 2025-03-20
0.735
best: 0.762 (DITR)
SOTA
Sonata: Self-Supervised Learning of Reliable Point Representations arXiv:2503.16429