| Method | Backbone | 1-Shot | 5-Shot |
| LEO (Rusu et al., 2019) | WRN-28-10 | 61.76 ± 0.08 | 77.59 ± 0.12 |
| SNAIL (Mishra et al., 2018) | ResNet-12 | 55.71 ± 0.99 | 68.88 ± 0.92 |
| AdaResNet (Munkhdalai et al., 2017) | ResNet-12 | 56.88 ± 0.62 | 71.94 ± 0.57 |
| TADAM (Oreshkin et al., 2018) | ResNet-12 | 58.50 ± 0.30 | 76.70 ± 0.30 |
| MTL (Sun et al., 2019) | ResNet-12 | 61.20 ± 1.80 | 75.50 ± 0.80 |
| MetaOptNet (Lee et al., 2019) | ResNet-12 | 60.33 ± 0.61 | 76.61 ± 0.46 |
| Meta-Baseline(Chen et al., 2021) | ResNet-12 | 63.17 ± 0.23 | 79.26 ± 0.17 |
| Our Method | ResNet-12 | 64.40 ± 0.18 | 80.28 ± 0.19 |