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/TagAlign

TagAlign

Reported on 21 benchmarks across 3 tasks · 1 paper · 13 SOTA

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

Medical7 results

Semantic SegmentationonCOCO-Stuff-171
mIoU· 2023-12-21
25.3
best: 34 (CorrCLIP)
SOTA
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
Semantic SegmentationonADE20K
Mean IoU (val)· 2023-12-21
17.3
best: 30.7 (CorrCLIP)
SOTA
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
Semantic SegmentationonPASCAL Context-59
mIoU· 2023-12-21
37.6
best: 50.8 (CorrCLIP)
SOTA
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
Semantic SegmentationonPascalVOC-20
mIoU· 2023-12-21
87.9
best: 91.8 (CorrCLIP)
SOTA
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
Semantic SegmentationonCOCO-Object
mIoU· 2023-12-21
33.3
best: 49.4 (CorrCLIP)
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
Semantic SegmentationonCityscapes val
mIoU· 2023-12-21
27.5
best: 90.3 (EfficientPS (Cityscapes-fine))
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
Semantic SegmentationonPASCAL VOC
mIoU· 2023-12-21
53.9
best: 76.7 (CorrCLIP)
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149

Computer Vision7 results

Unsupervised Semantic SegmentationonCOCO-Stuff-171
mIoU· 2023-12-21
25.3
best: 34 (CorrCLIP)
SOTA
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
Unsupervised Semantic SegmentationonADE20K
Mean IoU (val)· 2023-12-21
17.3
best: 30.7 (CorrCLIP)
SOTA
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
Unsupervised Semantic SegmentationonCityscapes val
mIoU· 2023-12-21
27.5
best: 51.1 (CorrCLIP)
SOTA
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
Unsupervised Semantic SegmentationonPASCAL Context-59
mIoU· 2023-12-21
37.6
best: 50.8 (CorrCLIP)
SOTA
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
Unsupervised Semantic SegmentationonPascalVOC-20
mIoU· 2023-12-21
87.9
best: 91.8 (CorrCLIP)
SOTA
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
Unsupervised Semantic SegmentationonCOCO-Object
mIoU· 2023-12-21
33.3
best: 49.4 (CorrCLIP)
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
Unsupervised Semantic SegmentationonPASCAL VOC
mIoU· 2023-12-21
53.9
best: 76.7 (CorrCLIP)
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149

Audio7 results

10-shot image generationonCOCO-Stuff-171
mIoU· 2023-12-21
25.3
best: 34 (CorrCLIP)
SOTA
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
10-shot image generationonADE20K
Mean IoU (val)· 2023-12-21
17.3
best: 30.7 (CorrCLIP)
SOTA
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
10-shot image generationonPASCAL Context-59
mIoU· 2023-12-21
37.6
best: 50.8 (CorrCLIP)
SOTA
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
10-shot image generationonPascalVOC-20
mIoU· 2023-12-21
87.9
best: 91.8 (CorrCLIP)
SOTA
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
10-shot image generationonCOCO-Object
mIoU· 2023-12-21
33.3
best: 49.4 (CorrCLIP)
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
10-shot image generationonCityscapes val
mIoU· 2023-12-21
27.5
best: 90.3 (EfficientPS (Cityscapes-fine))
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149
10-shot image generationonPASCAL VOC
mIoU· 2023-12-21
53.9
best: 76.7 (CorrCLIP)
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification arXiv:2312.14149