Image Classification on CIFAR-100 200 labels
20.06Top-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 | 20.06 | 1.28 | |
| SoftMatch/FreeMatchBackbone=ViT [Dosovitskiy et al., 2021] / ResNet-50 [He et al., 2016], SemiReward=false2023.10 | 21.07 | — | |
| FlexMatch + SemiRewardBackbone=ViT [Dosovitskiy et al., 2021] / ResNet-50 [He et al., 2016], SemiReward=true2023.10 | 23.74 | 1.28 | |
| FlexMatchBackbone=ViT [Dosovitskiy et al., 2021] / ResNet-50 [He et al., 2016], SemiReward=false2023.10 | 25.72 | — | |
| Pseudo Label + SemiRewardBackbone=ViT [Dosovitskiy et al., 2021] / ResNet-50 [He et al., 2016], SemiReward=true2023.10 | 31.94 | 1.28 | |
| Pseudo LabelBackbone=ViT [Dosovitskiy et al., 2021] / ResNet-50 [He et al., 2016], SemiReward=false2023.10 | 32.78 | — |