Fine-grained Classification on Stanford Cars (test)
7.3Top-1 ErrorFull FT
Evaluation Results
| Method | Links | |
|---|---|---|
| Full FTBackbone=SWIN-L, % Trainable parameters=100%, No backbone backpropagation=false2023.03 | 7.3 | |
| InCABackbone=SWIN-L, % Trainable parameters=3.7%, No backbone backpropagation=true2023.03 | 8.4 | |
| LoRABackbone=SWIN-L, % Trainable parameters=0.8%, No backbone backpropagation=false2023.03 | 9.6 | |
| AdaLNBackbone=SWIN-L, % Trainable parameters=0.1%, No backbone backpropagation=false2023.03 | 14.2 | |
| InCA (last)Backbone=SWIN-L, % Trainable parameters=3.7%, No backbone backpropagation=true2023.03 | 15 | |
| BitFitBackbone=SWIN-L, % Trainable parameters=0.1%, No backbone backpropagation=false2023.03 | 18.4 | |
| In. MLP-3Backbone=SWIN-L, % Trainable parameters=2.8%, No backbone backpropagation=true2023.03 | 22.4 | |
| MLP-3Backbone=SWIN-L, % Trainable parameters=2.8%, No backbone backpropagation=false2023.03 | 26 | |
| In. LPBackbone=SWIN-L, % Trainable parameters=0.1%, No backbone backpropagation=true2023.03 | 29.2 | |
| LPBackbone=SWIN-L, % Trainable parameters=0.1%, No backbone backpropagation=false2023.03 | 39 |