Image Classification on Indoor 40% independent noise (test)
68.13Top-1 AccREGSL
Evaluation Results
| Method | Links | |
|---|---|---|
| REGSLBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 68.13 | |
| ELRBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 66.34 | |
| APLBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 66.22 | |
| GCEBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 64.73 | |
| SCEBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 64.68 | |
| SATBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 63.43 | |
| l2-PGMBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 62.74 | |
| DACBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 59.73 | |
| LSBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 58.98 | |
| Fine-tuningBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 57.49 |