| Method | Backbone | 1-Shot | 5-Shot |
| MAML (Finn et al., 2017) | ConvNet-4 | 51.67 ± 1.81 | 70.30 ± 1.75 |
| Prototypical Networks* (Snell et al., 2017) | ConvNet-4 | 53.31 ± 0.89 | 72.69 ± 0.74 |
| Relation Networks* (Sung et al., 2018) | ConvNet-4 | 54.48 ± 0.93 | 71.32 ± 0.78 |
| LEO (Rusu et al., 2019) | WRN-28-10 | 66.33 ± 0.05 | 81.44 ± 0.09 |
| MetaOptNet (Lee et al., 2019) | ResNet-12 | 65.99 ± 0.72 | 81.56 ± 0.53 |
| Meta-Baseline(Chen et al., 2021) | ResNet-12 | 68.62 ± 0.27 | 83.29 ± 0.18 |
| Our Method | ResNet-12 | 69.47 ± 0.30 | 84.07 ± 0.25 |