Image Classification on Euro-SAT 20 labels
4.22Top-1 Error RateSoftMatch/FreeMatch + SemiReward
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SoftMatch/FreeMatch + SemiRewardBackbone=ViT [Dosovitskiy et al., 2021] / ResNet-50 [He et al., 2016], SemiReward=true2023.10 | 4.22 | 1.19 | |
| FlexMatch + SemiRewardBackbone=ViT [Dosovitskiy et al., 2021] / ResNet-50 [He et al., 2016], SemiReward=true2023.10 | 4.86 | 1.19 | |
| SoftMatch/FreeMatchBackbone=ViT [Dosovitskiy et al., 2021] / ResNet-50 [He et al., 2016], SemiReward=false2023.10 | 5.51 | — | |
| FlexMatchBackbone=ViT [Dosovitskiy et al., 2021] / ResNet-50 [He et al., 2016], SemiReward=false2023.10 | 5.54 | — | |
| Pseudo Label + SemiRewardBackbone=ViT [Dosovitskiy et al., 2021] / ResNet-50 [He et al., 2016], SemiReward=true2023.10 | 23.65 | 1.19 | |
| Pseudo LabelBackbone=ViT [Dosovitskiy et al., 2021] / ResNet-50 [He et al., 2016], SemiReward=false2023.10 | 25.25 | — |