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/R2D2 (ViT-B)

R2D2 (ViT-B)

Reported on 10 benchmarks across 1 task · 1 paper

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

Computer Vision10 results

Image RetrievalonMUGE Retrieval
Mean Recall· 2022-05-08
68.7
best: 83.6 (CN-CLIP (ViT-H/14))
CCMB: A Large-scale Chinese Cross-modal Benchmark arXiv:2205.03860
Image RetrievalonMUGE Retrieval
R@1· 2022-05-08
47.4
best: 68.9 (CN-CLIP (ViT-H/14))
CCMB: A Large-scale Chinese Cross-modal Benchmark arXiv:2205.03860
Image RetrievalonMUGE Retrieval
R@10· 2022-05-08
83.5
best: 93.1 (CN-CLIP (ViT-H/14))
CCMB: A Large-scale Chinese Cross-modal Benchmark arXiv:2205.03860
Image RetrievalonMUGE Retrieval
R@5· 2022-05-08
75.1
best: 88.7 (CN-CLIP (ViT-H/14))
CCMB: A Large-scale Chinese Cross-modal Benchmark arXiv:2205.03860
Image RetrievalonFlickr30k-CN
R@1· 2022-05-08
78.3
best: 85.9 (InternVL-G-FT)
CCMB: A Large-scale Chinese Cross-modal Benchmark arXiv:2205.03860
Image RetrievalonFlickr30k-CN
R@10· 2022-05-08
97
best: 98.7 (CN-CLIP (ViT-L/14@336px))
CCMB: A Large-scale Chinese Cross-modal Benchmark arXiv:2205.03860
Image RetrievalonFlickr30k-CN
R@5· 2022-05-08
94.6
best: 98.7 (InternVL-G-FT)
CCMB: A Large-scale Chinese Cross-modal Benchmark arXiv:2205.03860
Image RetrievalonCOCO-CN
R@1· 2022-05-08
75.1
best: 81.5 (CN-CLIP (ViT-H/14))
CCMB: A Large-scale Chinese Cross-modal Benchmark arXiv:2205.03860
Image RetrievalonCOCO-CN
R@10· 2022-05-08
98.1
best: 99.2 (CN-CLIP (ViT-L/14@336px))
CCMB: A Large-scale Chinese Cross-modal Benchmark arXiv:2205.03860
Image RetrievalonCOCO-CN
R@5· 2022-05-08
94.2
best: 97.1 (CN-CLIP (ViT-B/16))
CCMB: A Large-scale Chinese Cross-modal Benchmark arXiv:2205.03860