Image Classification on Caltech (Top-1 Accuracy)
96.5Top-1 AccuracyOurs
Evaluation results
| Method | Links | |
|---|---|---|
| OursShots=16, Backbone=ViT-B/16, Seeds=32025.12 | 96.5 | |
| OursShots=8, Backbone=ViT-B/16, Seeds=32025.12 | 95.9 | |
| OursShots=4, Backbone=ViT-B/16, Seeds=32025.12 | 95.7 | |
| OursShots=2, Backbone=ViT-B/16, Seeds=32025.12 | 95.1 | |
| OursShots=1, Backbone=ViT-B/16, Seeds=32025.12 | 94.8 | |
| ITO sub2Pre-training Dataset=DataComp-1B, Backbone=ViT-B/16, Training Epochs=10 epochs, Zero-shot protocol=EVA-CLIP2026.03 | 85.4 | |
| ITOPre-training Dataset=DataComp-1B, Backbone=ViT-B/16, Training Epochs=10 epochs, Zero-shot protocol=EVA-CLIP2026.03 | 85.1 | |
| CLIPPre-training Dataset=DataComp-1B, Backbone=ViT-B/16, Training Epochs=10 epochs, Zero-shot protocol=EVA-CLIP2026.03 | 84.7 | |
| ITOZero-shot=true, Backbone=ViT-B/16, Pre-training Dataset=Laion100M, Epochs=302026.03 | 83.8 | |
| CLIPZero-shot=true, Backbone=ViT-B/16, Pre-training Dataset=Laion100M, Epochs=302026.03 | 81.5 | |
| SLIPZero-shot=true, Backbone=ViT-B/16, Pre-training Dataset=Laion100M, Epochs=302026.03 | 81.2 | |
| ITO sub3Backbone=ViT-B/16, Pre-training Dataset=CC3M-recap, Evaluation Protocol=Zero-shot2026.03 | 72.1 | |
| ITO sub2Backbone=ViT-B/16, Pre-training Dataset=CC3M-recap, Evaluation Protocol=Zero-shot2026.03 | 71.4 | |
| FLAIRBackbone=ViT-B/16, Pre-training Dataset=CC3M-recap, Evaluation Protocol=Zero-shot2026.03 | 69.8 |