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/CLS-SEG

CLS-SEG

Reported on 9 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.

Medical3 results

Semantic SegmentationonCOCO-Object
mIoU· 2023-12-20
35.3
best: 49.4 (CorrCLIP)
SOTA
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training arXiv:2312.12828
Semantic SegmentationonPASCAL VOC
mIoU· 2023-12-20
68.7
best: 76.7 (CorrCLIP)
SOTA
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training arXiv:2312.12828
Semantic SegmentationonCOCO-Stuff-27
mIoU· 2023-12-20
31
best: 43.6 (DiffSeg (512))
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training arXiv:2312.12828

Computer Vision3 results

Unsupervised Semantic SegmentationonCOCO-Object
mIoU· 2023-12-20
35.3
best: 49.4 (CorrCLIP)
SOTA
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training arXiv:2312.12828
Unsupervised Semantic SegmentationonPASCAL VOC
mIoU· 2023-12-20
68.7
best: 76.7 (CorrCLIP)
SOTA
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training arXiv:2312.12828
Unsupervised Semantic SegmentationonCOCO-Stuff-27
mIoU· 2023-12-20
31
best: 32.6 (ReCo+)
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training arXiv:2312.12828

Audio3 results

10-shot image generationonCOCO-Object
mIoU· 2023-12-20
35.3
best: 49.4 (CorrCLIP)
SOTA
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training arXiv:2312.12828
10-shot image generationonPASCAL VOC
mIoU· 2023-12-20
68.7
best: 76.7 (CorrCLIP)
SOTA
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training arXiv:2312.12828
10-shot image generationonCOCO-Stuff-27
mIoU· 2023-12-20
31
best: 43.6 (DiffSeg (512))
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training arXiv:2312.12828