ML Research Wiki / Benchmarks / Image Retrieval / COCO-CN

COCO-CN

Image Retrieval Benchmark

Performance Over Time

📊 Showing 9 results | 📏 Metric: R@1

Top Performing Models

Rank Model Paper R@1 Date Code
1 CN-CLIP (ViT-H/14) Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese 81.50 2022-11-02 📦 ofa-sys/chinese-clip
2 CN-CLIP (ViT-L/14@336px) Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese 80.10 2022-11-02 📦 ofa-sys/chinese-clip
3 R2D2 (ViT-L/14) CCMB: A Large-scale Chinese Cross-modal Benchmark 79.10 2022-05-08 📦 yuxie11/R2D2
4 CN-CLIP (ViT-L/14) Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese 78.90 2022-11-02 📦 ofa-sys/chinese-clip
5 CN-CLIP (ViT-B/16) Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese 77.00 2022-11-02 📦 ofa-sys/chinese-clip
6 R2D2 (ViT-B) CCMB: A Large-scale Chinese Cross-modal Benchmark 75.10 2022-05-08 📦 yuxie11/R2D2
7 Wukong (ViT-L/14) Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark 74.00 2022-02-14 📦 0jason000/wukong
8 Wukong (ViT-B/32) Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark 67.00 2022-02-14 📦 0jason000/wukong
9 CN-CLIP (RN50) Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese 66.80 2022-11-02 📦 ofa-sys/chinese-clip

All Papers (9)

ofa-sys/chinese-clip
ofa-sys/chinese-clip
yuxie11/R2D2
ofa-sys/chinese-clip
ofa-sys/chinese-clip
yuxie11/R2D2
0jason000/wukong
0jason000/wukong
ofa-sys/chinese-clip