HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Image Retrieval On Flickr30K Cn

评估指标

R@1
R@10
R@5

评测结果

各个模型在此基准测试上的表现结果

模型名称
R@1
R@10
R@5
Paper TitleRepository
R2D2 (ViT-L/14)84.498.496.7CCMB: A Large-scale Chinese Cross-modal Benchmark
InternVL-G-FT85.997.198.7InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
CN-CLIP (RN50)66.794.189.4Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese
CN-CLIP (ViT-L/14@336px)84.498.797.1Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese
CN-CLIP (ViT-H/14)83.898.696.9Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese
CN-CLIP (ViT-B/16)79.197.494.8Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese
Wukong (ViT-B/32)67.694.289.6Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark
R2D2 (ViT-B)78.397.094.6CCMB: A Large-scale Chinese Cross-modal Benchmark
Wukong (ViT-L/14)77.497.094.5Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark
InternVL-C-FT85.297.098.5InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
CN-CLIP (ViT-L/14)82.798.696.7Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese
0 of 11 row(s) selected.