Image Classification on Indoor 20% independent noise (test)
72.51Top-1 AccREGSL
Evaluation Results
| Method | Links | |
|---|---|---|
| REGSLBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 72.51 | |
| ELRBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 71.43 | |
| GCEBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 70.45 | |
| APLBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 70.05 | |
| l2-PGMBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 69.45 | |
| SCEBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 69.43 | |
| SATBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 68.98 | |
| LSBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 67.04 | |
| Fine-tuningBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 65.02 | |
| DACBackbone=ResNet-18, Evaluation Protocol=Fine-tuning, Averaging across random seeds=32021.11 | 64.45 |