Fine-grained classification on Pets (Mean per class)
93.1Mean per Class AccuracyCLIP
Evaluation Results
| Method | Links | |
|---|---|---|
| CLIPPre-training Dataset=WIT-400M, Pre-training Data Type=Real, Backbone=ViT-B/162023.06 | 93.1 | |
| StableRepPre-training Dataset=RedCaps, Pre-training Data Type=Syn, Pre-training Schedule=105 epochs, Backbone=ViT-B/162023.06 | 91.7 | |
| CLIPPre-training Dataset=RedCaps, Pre-training Data Type=Real, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 91.6 | |
| StableRepPre-training Dataset=RedCaps, Pre-training Data Type=Syn, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 90.9 | |
| StableRepPre-training Dataset=CC12M, Pre-training Data Type=Syn, Pre-training Schedule=105 epochs, Backbone=ViT-B/162023.06 | 88.3 | |
| CLIPPre-training Dataset=RedCaps, Pre-training Data Type=Syn, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 88.2 | |
| StableRepPre-training Dataset=CC12M, Pre-training Data Type=Syn, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 87.5 | |
| SimCLRPre-training Dataset=RedCaps, Pre-training Data Type=Real, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 83 | |
| SimCLRPre-training Dataset=RedCaps, Pre-training Data Type=Syn, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 79.6 |