Classification on Stanford Cars 50% labels (test)
0.9114AccuracySelf-Tuning+HCR
Evaluation Results
| Method | Links | |
|---|---|---|
| Self-Tuning+HCRBackbone=ResNet-50, Pre-trained=ImageNet, Label Proportion=50%2022.06 | 0.9114 | |
| Self-TuningBackbone=ResNet-50, Pre-trained=ImageNet, Label Proportion=50%2022.06 | 0.8983 | |
| FixMatchBackbone=ResNet-50, Pre-trained=ImageNet, Label Proportion=50%2022.06 | 0.8478 | |
| Pseudo-LabelingBackbone=ResNet-50, Pre-trained=ImageNet, Label Proportion=50%2022.06 | 0.7871 | |
| SimCLRv2Backbone=ResNet-50, Pre-trained=ImageNet, Label Proportion=50%2022.06 | 0.7749 | |
| Mean TeacherBackbone=ResNet-50, Pre-trained=ImageNet, Label Proportion=50%2022.06 | 0.7424 | |
| UDABackbone=ResNet-50, Pre-trained=ImageNet, Label Proportion=50%2022.06 | 0.7186 | |
| Pi-modelBackbone=ResNet-50, Pre-trained=ImageNet, Label Proportion=50%2022.06 | 0.6418 |