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/TTD (MaskCLIP)

TTD (MaskCLIP)

Reported on 24 benchmarks across 4 tasks · 1 paper · 1 SOTA

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

Computer Vision10 results

Unsupervised Semantic SegmentationonCityscapes val
mIoU· 2024-03-30
32
best: 51.1 (CorrCLIP)
SOTA
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Unsupervised Semantic SegmentationonCOCO-Stuff-171
mIoU· 2024-03-30
19.4
best: 34 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Unsupervised Semantic SegmentationonCOCO-Object
mIoU· 2024-03-30
26.5
best: 49.4 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Unsupervised Semantic SegmentationonADE20K
Mean IoU (val)· 2024-03-30
12.7
best: 30.7 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Unsupervised Semantic SegmentationonPASCAL Context-59
mIoU· 2024-03-30
31
best: 50.8 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Unsupervised Semantic SegmentationonPASCAL VOC
mIoU· 2024-03-30
43.1
best: 76.7 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Open Vocabulary Semantic SegmentationonCOCO-Stuff-171
mIoU· 2024-03-30
19.4
best: 23.7 (TTD (TCL))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Open Vocabulary Semantic SegmentationonCityscapes
mIoU· 2024-03-30
27
best: 56.2 (FC-CLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Open Vocabulary Semantic SegmentationonPASCAL Context-59
mIoU· 2024-03-30
31
best: 64.6 (HyperSeg)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Open Vocabulary Semantic SegmentationonADE20K-150
mIoU· 2024-03-30
12.7
best: 38.2 (Mask-Adapter)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384

Medical7 results

Semantic SegmentationonCC3M-TagMask
mIoU· 2024-03-30
50.2
best: 65.5 (TTD (TCL))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Semantic SegmentationonCOCO-Stuff-171
mIoU· 2024-03-30
19.4
best: 34 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Semantic SegmentationonCOCO-Object
mIoU· 2024-03-30
26.5
best: 49.4 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Semantic SegmentationonADE20K
Mean IoU (val)· 2024-03-30
12.7
best: 30.7 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Semantic SegmentationonCityscapes val
mIoU· 2024-03-30
32
best: 90.3 (EfficientPS (Cityscapes-fine))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Semantic SegmentationonPASCAL Context-59
mIoU· 2024-03-30
31
best: 50.8 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Semantic SegmentationonPASCAL VOC
mIoU· 2024-03-30
43.1
best: 76.7 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384

Audio7 results

10-shot image generationonCC3M-TagMask
mIoU· 2024-03-30
50.2
best: 65.5 (TTD (TCL))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
10-shot image generationonCOCO-Stuff-171
mIoU· 2024-03-30
19.4
best: 34 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
10-shot image generationonCOCO-Object
mIoU· 2024-03-30
26.5
best: 49.4 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
10-shot image generationonADE20K
Mean IoU (val)· 2024-03-30
12.7
best: 30.7 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
10-shot image generationonCityscapes val
mIoU· 2024-03-30
32
best: 90.3 (EfficientPS (Cityscapes-fine))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
10-shot image generationonPASCAL Context-59
mIoU· 2024-03-30
31
best: 50.8 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
10-shot image generationonPASCAL VOC
mIoU· 2024-03-30
43.1
best: 76.7 (CorrCLIP)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384