Image-Text Retrieval on COCO & Flickr30k Retrieval (test)
69.44Mean Recall (Zero-shot)TuneCLIP
Evaluation Results
| Method | Links | |
|---|---|---|
| TuneCLIPBase Model=SigLIP ViT-B/16, WCT. (hrs)=9.272026.01 | 69.44 | |
| BaselineBase Model=SigLIP ViT-B/16, WCT. (hrs)=N/A2026.01 | 69.32 | |
| TuneCLIPBase Model=OpenAI ViT-B/16, WCT. (hrs)=8.622026.01 | 64.12 | |
| OpenCLIPBase Model=OpenAI ViT-B/16, WCT. (hrs)=5.462026.01 | 57.81 | |
| BaselineBase Model=OpenAI ViT-B/16, WCT. (hrs)=N/A2026.01 | 57.46 | |
| FastCLIPBase Model=OpenAI ViT-B/16, WCT. (hrs)=4.212026.01 | 51.88 | |
| OpenCLIPBase Model=SigLIP ViT-B/16, WCT. (hrs)=7.552026.01 | 51.54 | |
| FastCLIPBase Model=SigLIP ViT-B/16, WCT. (hrs)=4.282026.01 | 43.37 |