Few-shot Image Classification on MiniImageNet 5-way 1-shot
93.1AccuracyPMF
Evaluation results
| Method | Links | ||
|---|---|---|---|
| PMFBackbone=ViT-small, Training strategy=Self-Supervised + MT, Extra data=false, Extra labels=false2024.03 | 93.1 | — | |
| PT-MAPBackbone=WRN-28-10, Training strategy=Transductive, Extra data=false, Extra labels=true2024.03 | 82.9 | 0.3 | |
| CNAPS + FETIBackbone=WRN-28-10, Training strategy=Transductive, Extra data=false, Extra labels=true2024.03 | 79.9 | 0.8 | |
| DIPABackbone=ViT-small, Training strategy=Self-Supervised, Extra data=false, Extra labels=false2024.03 | 79.6 | 0.7 | |
| EPNet + SSLBackbone=WRN-28-10, Training strategy=Self-Supervised, Extra data=false, Extra labels=false2024.03 | 79.2 | 0.9 | |
| ProtoNetBackbone=AMDIM ResNet, Training strategy=Self-Supervised, Extra data=false, Extra labels=false2024.03 | 76.8 | 0.2 | |
| PLCMBackbone=ResNet12, Training strategy=Semi-Supervised, Extra data=false, Extra labels=true2024.03 | 72.1 | 1.1 | |
| LSTBackbone=ResNet12, Training strategy=Semi-Supervised, Extra data=false, Extra labels=true2024.03 | 70.1 | 1.9 | |
| SIBBackbone=WRN-28-10, Training strategy=Transductive, Extra data=false, Extra labels=true2024.03 | 70 | 0.6 | |
| FewTureBackbone=ViT-small, Training strategy=Self-Supervised, Extra data=false, Extra labels=false2024.03 | 68 | 0.9 | |
| Fine-tuningBackbone=WRN-28-10, Training strategy=Transductive, Extra data=false, Extra labels=true2024.03 | 65.7 | 0.7 | |
| RS-FSLBackbone=ResNet12, Training strategy=Inductive, Extra data=true, Extra labels=false2024.03 | 65.3 | 0.8 | |
| Meta-BaselineBackbone=ResNet12, Training strategy=Inductive, Extra data=false, Extra labels=false2024.03 | 63.2 | 0.2 | |
| ProtoNetBackbone=WRN-28-10, Training strategy=Self-Supervised, Extra data=false, Extra labels=false2024.03 | 62.9 | 0.5 | |
| MetaOpt-SVMBackbone=ResNet12, Training strategy=Inductive, Extra data=false, Extra labels=false2024.03 | 62.6 | 0.6 | |
| HTChannels=482022.01 | 55.1 | — | |
| RFSChannels=482022.01 | 54.2 | — | |
| HTChannels=322022.01 | 53.8 | — | |
| MAML++Channels=482022.01 | 52.2 | — | |
| RFSChannels=322022.01 | 51.5 | — | |
| HTChannels=162022.01 | 50.2 | — | |
| MAML++Channels=322022.01 | 49.4 | — | |
| RFSChannels=162022.01 | 49.4 | — | |
| Baseline++Backbone=CNN-4-64, Training strategy=Inductive, Extra data=false, Extra labels=false2024.03 | 48.2 | 0.8 | |
| MAML++Channels=162022.01 | 46.6 | — | |
| HTChannels=82022.01 | 45.5 | — | |
| RFSChannels=82022.01 | 44 | — | |
| MAML++Channels=82022.01 | 43.9 | — |