5-way 5-shot Image Classification on FC100 (test)
67.66AccuracyR2-D2 (best)
Evaluation results
| Method | Links | |
|---|---|---|
| R2-D2 (best)Task Augmentation=Rotating, Configuration=best (ensemble + val)2020.02 | 67.66 | |
| M-SVM (best)Task Augmentation=Rotating, Configuration=best (ensemble + val)2020.02 | 67.17 | |
| HCTransformers-Classifierbackbone=ViT-S2022.03 | 66.42 | |
| IEbackbone=ResNet-122022.03 | 65.3 | |
| PALbackbone=ResNet-122022.03 | 64 | |
| TPMNbackbone=ResNet-122022.03 | 63.26 | |
| DeepEMDbackbone=ResNet-122022.03 | 63.22 | |
| BMLbackbone=ResNet-122022.03 | 63.03 | |
| M-SVM2020.02 | 62.5 | |
| HCTransformers-Cosinebackbone=ViT-S2022.03 | 61.49 | |
| MN + MCbackbone=ResNet-122022.03 | 61.33 | |
| ConstellationNetbackbone=ResNet-122022.03 | 59.7 | |
| ALFA+METALbackbone=ResNet-122022.03 | 58.44 | |
| MixtFSLbackbone=ResNet-122022.03 | 58.39 | |
| MTL2020.02 | 57.6 | |
| SimSiam + AugSelfBackbone=ResNet-18, Pre-training Dataset=STL102021.11 | 56.26 | |
| TADAM2020.02 | 56.1 | |
| MoCo v2 + AugSelfBackbone=ResNet-18, Pre-training Dataset=STL102021.11 | 55.58 | |
| SimSiam + AugSelfBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.11 | 55.27 | |
| ProtoNets2020.02 | 52.5 | |
| SimSiamBackbone=ResNet-18, Pre-training Dataset=STL102021.11 | 51.49 | |
| Baseline-Cosinebackbone=ViT-S2022.03 | 50.93 | |
| SimSiamBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.11 | 50.36 | |
| MoCo v2Backbone=ResNet-18, Pre-training Dataset=STL102021.11 | 49.26 | |
| Supervised + AugSelfBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.11 | 48.89 | |
| MoCo v2 + AugSelfBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.11 | 48.77 | |
| SupervisedBackbone=ResNet-50, Pre-training Dataset=ImageNet1002021.11 | 46.59 | |
| MoCo v2Backbone=ResNet-50, Pre-training Dataset=ImageNet1002021.11 | 43.88 |