Few-shot Image Classification on CIFAR-FS 5-way 1-shot
87.7Mean AccuracyPT-MAP
Evaluation results
| Method | Links | ||
|---|---|---|---|
| PT-MAPBackbone=WRN-28-10, Training strategy=Transductive, Extra data=false, Extra labels=true2024.03 | 87.7 | 0.2 | |
| PMFBackbone=ViT-small, Training strategy=Self-Supervised + MT, Extra data=false, Extra labels=false2024.03 | 81.1 | — | |
| SIBBackbone=WRN-28-10, Training strategy=Transductive, Extra data=false, Extra labels=true2024.03 | 80 | 0.6 | |
| PLCMBackbone=ResNet12, Training strategy=Semi-Supervised, Extra data=false, Extra labels=true2024.03 | 77.6 | 1.2 | |
| Fine-tuningBackbone=WRN-28-10, Training strategy=Transductive, Extra data=false, Extra labels=true2024.03 | 76.6 | 0.7 | |
| FewTureBackbone=ViT-small, Training strategy=Self-Supervised, Extra data=false, Extra labels=false2024.03 | 76.1 | 0.9 | |
| ProtoNetBackbone=WRN-28-10, Training strategy=Self-Supervised, Extra data=false, Extra labels=false2024.03 | 73.6 | 0.3 | |
| MetaOpt-SVMBackbone=ResNet12, Training strategy=Inductive, Extra data=false, Extra labels=false2024.03 | 72 | 0.7 | |
| DIPABackbone=ViT-small, Training strategy=Self-Supervised, Extra data=false, Extra labels=false2024.03 | 65.2 | 0.9 |