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 (w/o fine-tuning)

TTD (w/o fine-tuning)

Reported on 15 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Methodology10 results

Multi-Label Text ClassificationonCC3M-TagMask
Accuracy· 2024-03-30
91
SOTA
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
ClassificationonCC3M-TagMask
Accuracy· 2024-03-30
91
SOTA
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Multi-Label Text ClassificationonCC3M-TagMask
F1· 2024-03-30
78.5
best: 82.8 (TTD (w/ fine-tuning))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Multi-Label Text ClassificationonCC3M-TagMask
Precision· 2024-03-30
82.9
best: 88.3 (TTD (w/ fine-tuning))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Multi-Label Text ClassificationonCC3M-TagMask
Recall· 2024-03-30
74.5
best: 83.7 (NLTK)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Multi-Label Text ClassificationonCC3M-TagMask
mAP· 2024-03-30
90.3
best: 93.7 (TTD (w/ fine-tuning))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
ClassificationonCC3M-TagMask
F1· 2024-03-30
78.5
best: 82.8 (TTD (w/ fine-tuning))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
ClassificationonCC3M-TagMask
Precision· 2024-03-30
82.9
best: 88.3 (TTD (w/ fine-tuning))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
ClassificationonCC3M-TagMask
Recall· 2024-03-30
74.5
best: 83.7 (NLTK)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
ClassificationonCC3M-TagMask
mAP· 2024-03-30
90.3
best: 93.7 (TTD (w/ fine-tuning))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384

Natural Language Processing5 results

Text ClassificationonCC3M-TagMask
Accuracy· 2024-03-30
91
SOTA
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Text ClassificationonCC3M-TagMask
F1· 2024-03-30
78.5
best: 82.8 (TTD (w/ fine-tuning))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Text ClassificationonCC3M-TagMask
Precision· 2024-03-30
82.9
best: 88.3 (TTD (w/ fine-tuning))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Text ClassificationonCC3M-TagMask
Recall· 2024-03-30
74.5
best: 83.7 (NLTK)
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384
Text ClassificationonCC3M-TagMask
mAP· 2024-03-30
90.3
best: 93.7 (TTD (w/ fine-tuning))
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias arXiv:2404.00384