Image Classification on ImageNet 1K (val) (Zero-Shot Accuracy)
83.4Zero-Shot AccuracySigLIP2-So/16-256
Evaluation results
| Method | Links | |
|---|---|---|
| SigLIP2-So/16-256Pre-trained Backbone=SigLIP2-So/16, Resolution=2562025.03 | 83.4 | |
| SigLIP-So/14-384Pre-trained Backbone=SigLIP-So/14, Resolution=3842025.03 | 83.2 | |
| DualTokenPre-trained Backbone=SigLIP2-So/16-2562025.03 | 82.3 | |
| DualTokenPre-trained Backbone=SigLIP-So/14-3842025.03 | 82 | |
| ViTamin-L/16-256Pre-trained Backbone=ViTamin-L/16, Resolution=2562025.03 | 81.2 | |
| SigLIP-L/16-256Pre-trained Backbone=SigLIP-L/16, Resolution=2562025.03 | 80.5 | |
| TokLIPPre-trained Backbone=SigLIP2-So/16-3842025.03 | 80 | |
| DualTokenPre-trained Backbone=SigLIP-L/16-2562025.03 | 79.8 | |
| QLIPResolution=392px2025.03 | 79.1 | |
| UniTok2025.03 | 78.6 | |
| VILA-UPre-trained Backbone=SigLIP-So/14-3842025.03 | 78 | |
| CLIP-L/14-336Pre-trained Backbone=CLIP-L/14, Resolution=3362025.03 | 76.6 | |
| QLIPResolution=256px2025.03 | 74.3 | |
| VILA-UPre-trained Backbone=SigLIP-L/16-2562025.03 | 73.3 |