Fine-grained classification on VOC 2007
89.2Mean per Class AccCLIP
Evaluation Results
| Method | Links | |
|---|---|---|
| CLIPPre-training Dataset=WIT-400M, Pre-training Data Type=Real, Backbone=ViT-B/162023.06 | 89.2 | |
| StableRepPre-training Dataset=CC12M, Pre-training Data Type=Syn, Pre-training Schedule=105 epochs, Backbone=ViT-B/162023.06 | 87.9 | |
| StableRepPre-training Dataset=RedCaps, Pre-training Data Type=Syn, Pre-training Schedule=105 epochs, Backbone=ViT-B/162023.06 | 87.8 | |
| StableRepPre-training Dataset=CC12M, Pre-training Data Type=Syn, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 87.2 | |
| StableRepPre-training Dataset=RedCaps, Pre-training Data Type=Syn, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 86.6 | |
| CLIPPre-training Dataset=RedCaps, Pre-training Data Type=Real, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 85.4 | |
| CLIPPre-training Dataset=RedCaps, Pre-training Data Type=Syn, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 84.5 | |
| SimCLRPre-training Dataset=RedCaps, Pre-training Data Type=Real, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 80.9 | |
| SimCLRPre-training Dataset=RedCaps, Pre-training Data Type=Syn, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 80.4 |