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/PseudoSeg

PseudoSeg

Reported on 8 benchmarks across 2 tasks · 1 paper · 8 SOTA

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

Medical4 results

Semantic SegmentationonCOCO 1/512 labeled
Validation mIoU· 2020-10-19
29.8
best: 50.1 (SemiVL)
SOTA
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation arXiv:2010.09713
Semantic SegmentationonCOCO 1/128 labeled
Validation mIoU· 2020-10-19
39.1
best: 58.7 (UniMatch V2)
SOTA
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation arXiv:2010.09713
Semantic SegmentationonCOCO 1/64 labeled
Validation mIoU· 2020-10-19
41.8
best: 60.4 (UniMatch V2)
SOTA
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation arXiv:2010.09713
Semantic SegmentationonCOCO 1/32 labeled
Validation mIoU· 2020-10-19
43.6
best: 63.3 (UniMatch V2)
SOTA
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation arXiv:2010.09713

Audio4 results

10-shot image generationonCOCO 1/512 labeled
Validation mIoU· 2020-10-19
29.8
best: 50.1 (SemiVL)
SOTA
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation arXiv:2010.09713
10-shot image generationonCOCO 1/128 labeled
Validation mIoU· 2020-10-19
39.1
best: 58.7 (UniMatch V2)
SOTA
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation arXiv:2010.09713
10-shot image generationonCOCO 1/64 labeled
Validation mIoU· 2020-10-19
41.8
best: 60.4 (UniMatch V2)
SOTA
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation arXiv:2010.09713
10-shot image generationonCOCO 1/32 labeled
Validation mIoU· 2020-10-19
43.6
best: 63.3 (UniMatch V2)
SOTA
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation arXiv:2010.09713