5-way 5-shot Classification on CIFAR-FS
96Mean AccuracyPMF
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| PMFPretraining & Meta-training=PMF [22], Backbone=ViT-B/16, IbM2=false2023.05 | 96 | 4.1 | 73.1 | 82.2 | 89.2 | — | — | |
| IbM2Pretraining & Meta-training=PMF [22], Backbone=ViT-B/16, IbM2=true2023.05 | 96 | 4.1 | 74.1 | 81.8 | 89.2 | — | — | |
| IbM2Pretraining & Meta-training=PMF [22], Backbone=ViT-S/16, IbM2=true2023.05 | 95.7 | 4.2 | 73.3 | 81.7 | 88.7 | — | — | |
| PMFPretraining & Meta-training=PMF [22], Backbone=ViT-S/16, IbM2=false2023.05 | 95.5 | 4.2 | 74.7 | 81.8 | 88.5 | — | — | |
| IbM2Pretraining & Meta-training=PMF [22], Backbone=ResNet50, IbM2=true2023.05 | 91.6 | 5.3 | 73.3 | 76 | 83.2 | — | — | |
| PMFPretraining & Meta-training=PMF [22], Backbone=ResNet50, IbM2=false2023.05 | 91.3 | 5.5 | 71.2 | 75.1 | 82.7 | — | — | |
| S2M2RPretraining & Meta-training=S2M2R [28], Backbone=WRN-28-10, IbM2=false2023.05 | 87.7 | 7.1 | 54.7 | 67.9 | 76.8 | — | — | |
| IbM2Pretraining & Meta-training=S2M2R [28], Backbone=WRN-28-10, IbM2=true2023.05 | 87.7 | 7 | 54.9 | 68.1 | 77 | — | — | |
| IbM2Pretraining & Meta-training=Meta-Baseline [11], Backbone=ResNet12, IbM2=true2023.05 | 85.1 | 7.5 | 56.3 | 65.4 | 74.1 | — | — | |
| Meta-BaselinePretraining & Meta-training=Meta-Baseline [11], Backbone=ResNet12, IbM2=false2023.05 | 84.8 | 7.5 | 54.7 | 65.1 | 73.6 | — | — | |
| LRA2023.11 | — | — | — | — | — | 36.41 | 33.78 | |
| MAD2023.11 | — | — | — | — | — | 35.19 | 32.57 | |
| TDFML2023.11 | — | — | — | — | — | 58.25 | 56.12 |