Image-to-Text Retrieval on Flickr8k-Rephrased
89.4Recall@5CLIMP (VMamba)
Evaluation Results
| Method | Links | |
|---|---|---|
| CLIMP (VMamba)Vision Tower=VMamba, Text Tower=Mamba-12026.01 | 89.4 | |
| CLIMP (VMamba)Vision Tower=VMamba, Text Tower=Mamba-22026.01 | 88.2 | |
| RoPE-ViTVision Tower=RoPE-ViT, Text Tower=LLaMA2026.01 | 85.8 | |
| ViTVision Tower=ViT, Text Tower=LLaMA2026.01 | 82 | |
| NaFlexVision Tower=NaFlex, Text Tower=LLaMA2026.01 | 80.2 | |
| FlexViTVision Tower=FlexViT, Text Tower=LLaMA2026.01 | 75 |