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/STEGO

STEGO

Reported on 9 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Medical3 results

Semantic SegmentationonPotsdam-3
Accuracy· 2022-03-16
77
best: 83.3 (PriMaPs-EM+HP (DINO ViT-B/8))
SOTA
Unsupervised Semantic Segmentation by Distilling Feature Correspondences arXiv:2203.08414
Semantic SegmentationonCityscapes test
Accuracy· 2022-03-16
73.2
best: 84.3 (ViCE)
Unsupervised Semantic Segmentation by Distilling Feature Correspondences arXiv:2203.08414
Semantic SegmentationonCityscapes test
mIoU· 2022-03-16
21
best: 67.3 (EDANet)
Unsupervised Semantic Segmentation by Distilling Feature Correspondences arXiv:2203.08414

Computer Vision3 results

Unsupervised Semantic SegmentationonPotsdam-3
Accuracy· 2022-03-16
77
best: 83.3 (PriMaPs-EM+HP (DINO ViT-B/8))
SOTA
Unsupervised Semantic Segmentation by Distilling Feature Correspondences arXiv:2203.08414
Unsupervised Semantic SegmentationonCityscapes test
Accuracy· 2022-03-16
73.2
best: 84.3 (ViCE)
Unsupervised Semantic Segmentation by Distilling Feature Correspondences arXiv:2203.08414
Unsupervised Semantic SegmentationonCityscapes test
mIoU· 2022-03-16
21
best: 26.8 (CUPS)
Unsupervised Semantic Segmentation by Distilling Feature Correspondences arXiv:2203.08414

Audio3 results

10-shot image generationonPotsdam-3
Accuracy· 2022-03-16
77
best: 83.3 (PriMaPs-EM+HP (DINO ViT-B/8))
SOTA
Unsupervised Semantic Segmentation by Distilling Feature Correspondences arXiv:2203.08414
10-shot image generationonCityscapes test
Accuracy· 2022-03-16
73.2
best: 84.3 (ViCE)
Unsupervised Semantic Segmentation by Distilling Feature Correspondences arXiv:2203.08414
10-shot image generationonCityscapes test
mIoU· 2022-03-16
21
best: 67.3 (EDANet)
Unsupervised Semantic Segmentation by Distilling Feature Correspondences arXiv:2203.08414