Image-to-Text Retrieval on COCO 2017 (test)
71.1I2T ScoreJEST++
Evaluation Results
| Method | Links | |
|---|---|---|
| JEST++Variant=L, # Train=4B, FLOPS % (Per Iter.)=233, FLOPS % (Total)=232024.06 | 71.1 | |
| JEST++Variant=B, # Train=4B, FLOPS % (Per Iter.)=233, FLOPS % (Total)=232024.06 | 70.3 | |
| SigLIPVariant=L, # Train=40B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=1002024.06 | 69.5 | |
| Flexi-JEST++Variant=B, # Train=4B, FLOPS % (Per Iter.)=110, FLOPS % (Total)=112024.06 | 68 | |
| SILC-SVariant=B, # Train=20B, FLOPS % (Per Iter.)=380, FLOPS % (Total)=1902024.06 | 66.2 | |
| SigLIPVariant=B, # Train=40B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=1002024.06 | 65.2 | |
| EVA-CLIPVariant=L, # Train=4B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=102024.06 | 63.7 | |
| OpenCLIPVariant=L, # Train=32B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=802024.06 | 62.1 | |
| OpenCLIPVariant=B, # Train=34B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=852024.06 | 59.4 | |
| EVA-CLIPVariant=B, # Train=8B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=202024.06 | 58.7 | |
| LessIsMoreVariant=B, # Train=11B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=282024.06 | 58.3 | |
| CLIPVariant=L, # Train=13B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=322024.06 | 56.3 | |
| CLIPVariant=B, # Train=13B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=322024.06 | 52.4 |