5-way 1-shot Classification on CIFAR-FS
90.3Mean AccuracyIbM2
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| IbM2Pretraining & Meta-training=PMF [22], Backbone=ViT-B/16, IbM2=true2023.05 | 90.3 | 8 | 58.9 | 65.5 | 77.4 | — | — | |
| PMFPretraining & Meta-training=PMF [22], Backbone=ViT-B/16, IbM2=false2023.05 | 89.8 | 8.1 | 55.2 | 64.8 | 76.8 | — | — | |
| IbM2Pretraining & Meta-training=PMF [22], Backbone=ViT-S/16, IbM2=true2023.05 | 89 | 8.1 | 59.2 | 64.1 | 75.9 | — | — | |
| PMFPretraining & Meta-training=PMF [22], Backbone=ViT-S/16, IbM2=false2023.05 | 87.9 | 8.3 | 51.7 | 61.7 | 74.8 | — | — | |
| IbM2Pretraining & Meta-training=PMF [22], Backbone=ResNet50, IbM2=true2023.05 | 82.3 | 10.3 | 36.3 | 51.1 | 66.5 | — | — | |
| PMFPretraining & Meta-training=PMF [22], Backbone=ResNet50, IbM2=false2023.05 | 81.7 | 10.4 | 35.2 | 51.6 | 65.8 | — | — | |
| IbM2Pretraining & Meta-training=S2M2R [28], Backbone=WRN-28-10, IbM2=true2023.05 | 75.5 | 10.8 | 42.4 | 45.5 | 59.2 | — | — | |
| S2M2RPretraining & Meta-training=S2M2R [28], Backbone=WRN-28-10, IbM2=false2023.05 | 75.2 | 10.8 | 44 | 46.7 | 59.2 | — | — | |
| Meta-BaselinePretraining & Meta-training=Meta-Baseline [11], Backbone=ResNet12, IbM2=false2023.05 | 72.7 | 11.6 | 32 | 42.9 | 56.1 | — | — | |
| IbM2Pretraining & Meta-training=Meta-Baseline [11], Backbone=ResNet12, IbM2=true2023.05 | 72.3 | 11.5 | 32.8 | 42.3 | 55.7 | — | — | |
| LRA2023.11 | — | — | — | — | — | 30.12 | 28.03 | |
| MAD2023.11 | — | — | — | — | — | 29.24 | 26.16 | |
| TDFML2023.11 | — | — | — | — | — | 41.91 | 41.78 |