Image Classification on ImageNet-1K 1.0 (val) (Metrics 10-S and ZS)
80.5Zero-Shot AccuracySigLIP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SigLIPVariant=L, # Train=40B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=1002024.06 | 80.5 | 77.1 | |
| JEST++Variant=L, # Train=4B, FLOPS % (Per Iter.)=233, FLOPS % (Total)=232024.06 | 80.5 | 75.5 | |
| EVA-CLIPVariant=L, # Train=4B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=102024.06 | 79.8 | — | |
| JEST++Variant=B, # Train=4B, FLOPS % (Per Iter.)=233, FLOPS % (Total)=232024.06 | 76.9 | 70.3 | |
| SigLIPVariant=B, # Train=40B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=1002024.06 | 76.7 | 70.3 | |
| SILC-SVariant=B, # Train=20B, FLOPS % (Per Iter.)=380, FLOPS % (Total)=1902024.06 | 76.6 | 68.9 | |
| Flexi-JEST++Variant=B, # Train=4B, FLOPS % (Per Iter.)=110, FLOPS % (Total)=112024.06 | 75.8 | 68.2 | |
| CLIPVariant=L, # Train=13B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=322024.06 | 75.5 | — | |
| EVA-CLIPVariant=B, # Train=8B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=202024.06 | 74.7 | — | |
| OpenCLIPVariant=L, # Train=32B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=802024.06 | 74 | — | |
| LessIsMoreVariant=B, # Train=11B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=282024.06 | 70.8 | — | |
| OpenCLIPVariant=B, # Train=34B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=852024.06 | 70.2 | — | |
| CLIPVariant=B, # Train=13B, FLOPS % (Per Iter.)=100, FLOPS % (Total)=322024.06 | 68.3 | — |