Medical Image Classification on Cell (test)
95.3AccuracyFull fine-tuning
Evaluation results
| Method | Links | |
|---|---|---|
| Full fine-tuningBackbone=Swin-L, #Trainable Parameters=195M2025.06 | 95.3 | |
| LKABackbone=Swin-L, #Trainable Parameters=0.652M2025.06 | 94.5 | |
| LORABackbone=Swin-L, #Trainable Parameters=0.578M2025.06 | 94 | |
| AdapterformerBackbone=Swin-L, #Trainable Parameters=0.320M2025.06 | 93.9 | |
| CIATBackbone=Swin-L, #Trainable Parameters=0.966M2025.06 | 93.6 | |
| BitfitBackbone=Swin-L, #Trainable Parameters=0.313M2025.06 | 92.4 | |
| LOSSLESS ADAPTATIONBackbone=Swin-L, #Trainable Parameters=0.320M2025.06 | 92.4 | |
| RepAdapterBackbone=Swin-L, #Trainable Parameters=0.486M2025.06 | 92.4 | |
| ConvpassBackbone=Swin-L, #Trainable Parameters=0.661M2025.06 | 92.1 | |
| VPTBackbone=Swin-L, #Trainable Parameters=1.052M2025.06 | 91.7 | |
| AdapterBackbone=Swin-L, #Trainable Parameters=0.633M2025.06 | 91.4 | |
| Linear probingBackbone=Swin-L, #Trainable Parameters=0.006M2025.06 | 85.7 | |
| AIMBackbone=Swin-L, #Trainable Parameters=0.947M2025.06 | 84.9 | |
| ST-AdapterBackbone=Swin-L, #Trainable Parameters=0.334M2025.06 | 77.7 |