Fine-grained Classification on CIFAR-100
85.6AccuracyStableRep
Evaluation results
| Method | Links | |
|---|---|---|
| StableRepPre-training Dataset=RedCaps, Pre-training Data Type=Syn, Pre-training Schedule=105 epochs, Backbone=ViT-B/162023.06 | 85.6 | |
| StableRepPre-training Dataset=CC12M, Pre-training Data Type=Syn, Pre-training Schedule=105 epochs, Backbone=ViT-B/162023.06 | 84.7 | |
| StableRepPre-training Dataset=RedCaps, Pre-training Data Type=Syn, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 84.6 | |
| StableRepPre-training Dataset=CC12M, Pre-training Data Type=Syn, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 84.1 | |
| CLIPPre-training Dataset=WIT-400M, Pre-training Data Type=Real, Backbone=ViT-B/162023.06 | 83.1 | |
| CLIPPre-training Dataset=RedCaps, Pre-training Data Type=Real, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 78.9 | |
| SimCLRPre-training Dataset=RedCaps, Pre-training Data Type=Real, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 72 | |
| CLIPPre-training Dataset=RedCaps, Pre-training Data Type=Syn, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 71.4 | |
| SimCLRPre-training Dataset=RedCaps, Pre-training Data Type=Syn, Pre-training Schedule=35 epochs, Backbone=ViT-B/162023.06 | 65.4 |