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/TextRegion

TextRegion

Reported on 18 benchmarks across 3 tasks · 1 paper

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

Medical6 results

Semantic SegmentationonCOCO-Stuff-171
mIoU· 2025-05-29
31.2
best: 34 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
Semantic SegmentationonADE20K
Mean IoU (val)· 2025-05-29
27.3
best: 30.7 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
Semantic SegmentationonPASCAL Context-59
mIoU· 2025-05-29
46.1
best: 50.8 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
Semantic SegmentationonPASCAL Context-60
mIoU· 2025-05-29
41.2
best: 44.9 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
Semantic SegmentationonPascalVOC-20
mIoU· 2025-05-29
89.5
best: 91.8 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
Semantic SegmentationonPASCAL VOC
mIoU· 2025-05-29
73.1
best: 76.7 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769

Computer Vision6 results

Unsupervised Semantic SegmentationonCOCO-Stuff-171
mIoU· 2025-05-29
31.2
best: 34 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
Unsupervised Semantic SegmentationonADE20K
Mean IoU (val)· 2025-05-29
27.3
best: 30.7 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
Unsupervised Semantic SegmentationonPASCAL Context-59
mIoU· 2025-05-29
46.1
best: 50.8 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
Unsupervised Semantic SegmentationonPASCAL Context-60
mIoU· 2025-05-29
41.2
best: 44.9 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
Unsupervised Semantic SegmentationonPascalVOC-20
mIoU· 2025-05-29
89.5
best: 91.8 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
Unsupervised Semantic SegmentationonPASCAL VOC
mIoU· 2025-05-29
73.1
best: 76.7 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769

Audio6 results

10-shot image generationonCOCO-Stuff-171
mIoU· 2025-05-29
31.2
best: 34 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
10-shot image generationonADE20K
Mean IoU (val)· 2025-05-29
27.3
best: 30.7 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
10-shot image generationonPASCAL Context-59
mIoU· 2025-05-29
46.1
best: 50.8 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
10-shot image generationonPASCAL Context-60
mIoU· 2025-05-29
41.2
best: 44.9 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
10-shot image generationonPascalVOC-20
mIoU· 2025-05-29
89.5
best: 91.8 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769
10-shot image generationonPASCAL VOC
mIoU· 2025-05-29
73.1
best: 76.7 (CorrCLIP)
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models arXiv:2505.23769