Image Classification on CIFAR-100 SSL split 10000 labels (train test)
24.66Error RateCustomKD
Evaluation results
| Method | Links | |
|---|---|---|
| CustomKDCategory=KD, Backbone=WideResNet28-2, Pre-trained with=AdaMatch2025.03 | 24.66 | |
| DKDCategory=KD, Backbone=WideResNet28-2, Pre-trained with=AdaMatch2025.03 | 26.19 | |
| SimMatchCategory=SSL2025.03 | 26.42 | |
| FreeMatchCategory=SSL2025.03 | 27.17 | |
| SoftMatchCategory=SSL2025.03 | 27.26 | |
| Soft TargetCategory=KD, Backbone=WideResNet28-2, Pre-trained with=AdaMatch2025.03 | 27.66 | |
| LogitsCategory=KD, Backbone=WideResNet28-2, Pre-trained with=AdaMatch2025.03 | 28.16 | |
| FixMatchCategory=SSL2025.03 | 28.28 | |
| CCCategory=KD, Backbone=WideResNet28-2, Pre-trained with=AdaMatch2025.03 | 28.75 | |
| RKDCategory=KD, Backbone=WideResNet28-2, Pre-trained with=AdaMatch2025.03 | 29.11 | |
| FitNetCategory=KD, Backbone=WideResNet28-2, Pre-trained with=AdaMatch2025.03 | 29.41 | |
| AdaMatch*Category=SSL, Note=reproduced results using codes of USB benchmark2025.03 | 32.5 |