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/Trident

Trident

Reported on 24 benchmarks across 3 tasks · 1 paper · 22 SOTA

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

Medical8 results

Semantic SegmentationonCOCO-Stuff-171
mIoU· 2024-11-14
28.6
best: 34 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Semantic SegmentationonCOCO-Object
mIoU· 2024-11-14
42.2
best: 49.4 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Semantic SegmentationonADE20K
Mean IoU (val)· 2024-11-14
26.7
best: 30.7 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Semantic SegmentationonPASCAL Context-59
mIoU· 2024-11-14
44.3
best: 50.8 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Semantic SegmentationonPASCAL Context-60
mIoU· 2024-11-14
40.1
best: 44.9 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Semantic SegmentationonPascalVOC-20
mIoU· 2024-11-14
88.7
best: 91.8 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Semantic SegmentationonPASCAL VOC
mIoU· 2024-11-14
70.8
best: 76.7 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Semantic SegmentationonCityscapes val
mIoU· 2024-11-14
47.6
best: 90.3 (EfficientPS (Cityscapes-fine))
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219

Computer Vision8 results

Unsupervised Semantic SegmentationonCOCO-Stuff-171
mIoU· 2024-11-14
28.6
best: 34 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Unsupervised Semantic SegmentationonCOCO-Object
mIoU· 2024-11-14
42.2
best: 49.4 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Unsupervised Semantic SegmentationonADE20K
Mean IoU (val)· 2024-11-14
26.7
best: 30.7 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Unsupervised Semantic SegmentationonCityscapes val
mIoU· 2024-11-14
47.6
best: 51.1 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Unsupervised Semantic SegmentationonPASCAL Context-59
mIoU· 2024-11-14
44.3
best: 50.8 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Unsupervised Semantic SegmentationonPASCAL Context-60
mIoU· 2024-11-14
40.1
best: 44.9 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Unsupervised Semantic SegmentationonPascalVOC-20
mIoU· 2024-11-14
88.7
best: 91.8 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
Unsupervised Semantic SegmentationonPASCAL VOC
mIoU· 2024-11-14
70.8
best: 76.7 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219

Audio8 results

10-shot image generationonCOCO-Stuff-171
mIoU· 2024-11-14
28.6
best: 34 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
10-shot image generationonCOCO-Object
mIoU· 2024-11-14
42.2
best: 49.4 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
10-shot image generationonADE20K
Mean IoU (val)· 2024-11-14
26.7
best: 30.7 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
10-shot image generationonPASCAL Context-59
mIoU· 2024-11-14
44.3
best: 50.8 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
10-shot image generationonPASCAL Context-60
mIoU· 2024-11-14
40.1
best: 44.9 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
10-shot image generationonPascalVOC-20
mIoU· 2024-11-14
88.7
best: 91.8 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
10-shot image generationonPASCAL VOC
mIoU· 2024-11-14
70.8
best: 76.7 (CorrCLIP)
SOTA
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219
10-shot image generationonCityscapes val
mIoU· 2024-11-14
47.6
best: 90.3 (EfficientPS (Cityscapes-fine))
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation arXiv:2411.09219